FC openclaw-self-healing

4-tier autonomous self-healing and auto-recovery system for OpenClaw Gateway. Monitors gateway health, auto-restarts on crash, detects OAuth token expiry, kills zombie processes, and escalates to Claude Code AI for diagnosis when automated recovery fails. Use when your OpenClaw gateway crashes, stops responding, enters a restart loop, or needs automatic monitoring and recovery. Features watchdog, config validation, exponential backoff, Discord/Telegram alerts. macOS & Linux.

Not recommendedcritical or high security findings · low grade F

modbender/skill-library-mcp Agent Skills author: modbender MIT 41 files · 11 scripts body ≈ 751 tokens Open the sourcegithub.com↗ analyzed 3 d ago

4-tier autonomous self-healing and auto-recovery system for OpenClaw Gateway.

As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

Integration Discord Telegram GitHub Software development AI and agents Infrastructuretype and topics are labelled automatically from the skill text

Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode

JSON

Technical rating

33/100

safety, quality, tests

Safety 60%: 0
Quality 40%: 83
Run on models: none yet

Process rating

53/100

Has gaps

Result and completion w 14: 0
Inputs and preconditions w 11: 0
Failures and branches w 10: 0

the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.

For the model run — optional

Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 99

high Dangerous commands cmd-persistence docs/QUICKSTART.md:143

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
cp launchagent/com.openclaw.healthcheck.plist ~/Library/LaunchAgents/
```
high Dangerous commands cmd-persistence docs/QUICKSTART.md:146

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl load ~/Library/LaunchAgents/com.openclaw.healthcheck.plist
```
high Dangerous commands cmd-persistence docs/QUICKSTART.md:298

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl unload ~/Library/LaunchAgents/com.openclaw.healthcheck.plist
```
high Dangerous commands cmd-persistence docs/QUICKSTART.md:301

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
chmod 644 ~/Library/LaunchAgents/com.openclaw.healthcheck.plist
```
high Dangerous commands cmd-persistence docs/QUICKSTART.md:304

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl load ~/Library/LaunchAgents/com.openclaw.healthcheck.plist
```
high Dangerous commands cmd-persistence docs/self-healing-QUICKSTART.md:143

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
cp launchagent/com.openclaw.healthcheck.plist ~/Library/LaunchAgents/
```
high Dangerous commands cmd-persistence docs/self-healing-QUICKSTART.md:146

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl load ~/Library/LaunchAgents/com.openclaw.healthcheck.plist
```
high Dangerous commands cmd-persistence docs/self-healing-QUICKSTART.md:298

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl unload ~/Library/LaunchAgents/com.openclaw.healthcheck.plist
```
high Dangerous commands cmd-persistence docs/self-healing-QUICKSTART.md:301

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
chmod 644 ~/Library/LaunchAgents/com.openclaw.healthcheck.plist
```
high Dangerous commands cmd-persistence docs/self-healing-QUICKSTART.md:304

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl load ~/Library/LaunchAgents/com.openclaw.healthcheck.plist
```
high Dangerous commands cmd-persistence docs/self-healing-README.md:132

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
cp launchagent/com.openclaw.healthcheck.plist ~/Library/LaunchAgents/
```
high Dangerous commands cmd-persistence docs/self-healing-README.md:133

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl load ~/Library/LaunchAgents/com.openclaw.healthcheck.plist
```
high Dangerous commands cmd-persistence docs/self-healing-system.md:97

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl load ~/Library/LaunchAgents/com.openclaw.healthcheck.plist
```
high Dangerous commands cmd-persistence docs/self-healing-system.md:102

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl unload ~/Library/LaunchAgents/com.openclaw.healthcheck.plist
```
high Dangerous commands cmd-persistence docs/self-healing-system.md:339

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl unload ~/Library/LaunchAgents/com.openclaw.healthcheck.plist
```
high Dangerous commands cmd-persistence docs/self-healing-TROUBLESHOOTING.md:53

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
ls ~/Library/LaunchAgents/ai.openclaw.watchdog.plist
```
high Dangerous commands cmd-persistence docs/self-healing-TROUBLESHOOTING.md:63

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl unload ~/Library/LaunchAgents/ai.openclaw.watchdog.plist
```
high Dangerous commands cmd-persistence docs/self-healing-TROUBLESHOOTING.md:64

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl load ~/Library/LaunchAgents/ai.openclaw.watchdog.plist
```
high Dangerous commands cmd-persistence docs/self-healing-TROUBLESHOOTING.md:88

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl load ~/Library/LaunchAgents/com.openclaw.healthcheck.plist
```
high Dangerous commands cmd-persistence docs/self-healing-TROUBLESHOOTING.md:94

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
cat ~/Library/LaunchAgents/com.openclaw.healthcheck.plist | grep ProgramArguments -A 2
```
high Dangerous commands cmd-persistence docs/TROUBLESHOOTING.md:53

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
ls ~/Library/LaunchAgents/ai.openclaw.watchdog.plist
```
high Dangerous commands cmd-persistence docs/TROUBLESHOOTING.md:63

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl unload ~/Library/LaunchAgents/ai.openclaw.watchdog.plist
```
high Dangerous commands cmd-persistence docs/TROUBLESHOOTING.md:64

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl load ~/Library/LaunchAgents/ai.openclaw.watchdog.plist
```
high Dangerous commands cmd-persistence docs/TROUBLESHOOTING.md:88

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl load ~/Library/LaunchAgents/com.openclaw.healthcheck.plist
```
high Dangerous commands cmd-persistence docs/TROUBLESHOOTING.md:94

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
cat ~/Library/LaunchAgents/com.openclaw.healthcheck.plist | grep ProgramArguments -A 2
```
high Dangerous commands cmd-pipe-to-shell install.sh:71

Downloads and executes remote code from an unrecognised host (pipe to shell)
```
exec bash <(curl -sSL "$REPO_RAW/install-linux.sh") "$@"
```
high Dangerous commands cmd-persistence install.sh:320

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl bootstrap "gui/$(id -u)" "$watchdog_plist" 2>/dev/null || launchctl load "$watchdog_plist"
```
high Dangerous commands cmd-persistence install.sh:364

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl bootstrap "gui/$(id -u)" "$healthcheck_plist" 2>/dev/null || launchctl load "$healthcheck_plist"
```
high Dangerous commands cmd-persistence README.md:296

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
cp launchagent/com.openclaw.healthcheck.plist ~/Library/LaunchAgents/
```
high Dangerous commands cmd-persistence README.md:297

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl load ~/Library/LaunchAgents/com.openclaw.healthcheck.plist
```
high Dangerous commands cmd-persistence references/self-healing-system.md:97

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl load ~/Library/LaunchAgents/com.openclaw.healthcheck.plist
```
high Dangerous commands cmd-persistence references/self-healing-system.md:102

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl unload ~/Library/LaunchAgents/com.openclaw.healthcheck.plist
```
high Dangerous commands cmd-persistence references/self-healing-system.md:339

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl unload ~/Library/LaunchAgents/com.openclaw.healthcheck.plist
```
high Dangerous commands cmd-persistence references/self-healing-TROUBLESHOOTING.md:53

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
ls ~/Library/LaunchAgents/ai.openclaw.watchdog.plist
```
high Dangerous commands cmd-persistence references/self-healing-TROUBLESHOOTING.md:63

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl unload ~/Library/LaunchAgents/ai.openclaw.watchdog.plist
```
high Dangerous commands cmd-persistence references/self-healing-TROUBLESHOOTING.md:64

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl load ~/Library/LaunchAgents/ai.openclaw.watchdog.plist
```
high Dangerous commands cmd-persistence references/self-healing-TROUBLESHOOTING.md:88

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl load ~/Library/LaunchAgents/com.openclaw.healthcheck.plist
```
high Dangerous commands cmd-persistence references/self-healing-TROUBLESHOOTING.md:94

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
cat ~/Library/LaunchAgents/com.openclaw.healthcheck.plist | grep ProgramArguments -A 2
```
high Dangerous commands cmd-persistence scripts/gateway-watchdog.sh:217

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl bootstrap "gui/$(id -u)" "$LAUNCHD_PLIST" 2>/dev/null || true
```
high Dangerous commands cmd-persistence scripts/gateway-watchdog.sh:257

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl bootstrap "gui/$(id -u)" "$LAUNCHD_PLIST" 2>/dev/null || true
```
high Dangerous commands cmd-pipe-to-shell SKILL.md:64

Downloads and executes remote code from an unrecognised host (pipe to shell)
```
bash <(curl -fsSL https://raw.githubusercontent.com/Ramsbaby/openclaw-self-healing/main/install.sh)
```

Medium and low: 58

medium Dangerous commands cmd-pipe-to-shell CHANGELOG.md:104

Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)
```
- Single command: `curl -sSL .../install.sh | bash`
```
quoted
medium Dangerous commands cmd-shell-rc docs/fmp-api-setup.md:26

Writes to a shell startup file
```
echo 'export FMP_API_KEY="your_api_key_here"' >> ~/.zshrc
```
medium Dangerous commands cmd-pipe-to-shell-known-host docs/LINUX_SETUP.md:8

Pipe-to-shell installer from a well-known host (still executes remote code)
```
curl -sSL https://raw.githubusercontent.com/Ramsbaby/openclaw-self-healing/main/install.sh | bash
```
medium Dangerous commands cmd-pipe-to-shell-known-host docs/LINUX_SETUP.md:14

Pipe-to-shell installer from a well-known host (still executes remote code)
```
curl -sSL https://raw.githubusercontent.com/Ramsbaby/openclaw-self-healing/main/install-linux.sh | bash
```
medium Dangerous commands cmd-pipe-to-shell-known-host docs/LINUX_SETUP.md:19

Pipe-to-shell installer from a well-known host (still executes remote code)
```
curl -sSL https://raw.githubusercontent.com/Ramsbaby/openclaw-self-healing/main/install-linux.sh | bash -s -- --workspace ~/my-openclaw
```
medium Dangerous commands cmd-shell-rc docs/realtime-api-setup.md:21

Writes to a shell startup file
```
echo 'export FINNHUB_API_KEY="your_api_key_here"' >> ~/.zshrc
```
medium Dangerous commands cmd-persistence docs/self-healing-system.md:68

Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
```
- `~/Library/LaunchAgents/ai.openclaw.watchdog.plist`
```
quoted
medium Dangerous commands cmd-persistence docs/self-healing-system.md:83

Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
```
- `~/Library/LaunchAgents/com.openclaw.healthcheck.plist`
```
quoted
medium Dangerous commands cmd-persistence install.sh:282

Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
```
local watchdog_plist="$HOME/Library/LaunchAgents/ai.openclaw.watchdog.plist"
```
code literal
medium Dangerous commands cmd-persistence install.sh:326

Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
```
local healthcheck_plist="$HOME/Library/LaunchAgents/com.openclaw.healthcheck.plist"
```
code literal
medium Dangerous commands cmd-pipe-to-shell-known-host README.md:32

Pipe-to-shell installer from a well-known host (still executes remote code)
```
curl -fsSL https://raw.githubusercontent.com/Ramsbaby/openclaw-self-healing/main/scripts/demo-self-healing.sh | bash
```
medium Dangerous commands cmd-pipe-to-shell-known-host README.md:235

Pipe-to-shell installer from a well-known host (still executes remote code)
```
curl -sSL https://raw.githubusercontent.com/Ramsbaby/openclaw-self-healing/main/install.sh | bash
```
medium Dangerous commands cmd-pipe-to-shell-known-host README.md:246

Pipe-to-shell installer from a well-known host (still executes remote code)
```
curl -sSL https://raw.githubusercontent.com/Ramsbaby/openclaw-self-healing/main/install-linux.sh | bash
```
medium Dangerous commands cmd-pipe-to-shell-known-host README.md:251

Pipe-to-shell installer from a well-known host (still executes remote code)
```
curl -sSL https://raw.githubusercontent.com/Ramsbaby/openclaw-self-healing/main/install.sh | bash -s -- --workspace ~/my-openclaw
```
medium Dangerous commands cmd-persistence references/LINUX_SETUP.md:94

Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation table row)
```
| `~/Library/LaunchAgents/` | `/etc/systemd/system/` |
```
table
medium Dangerous commands cmd-persistence references/self-healing-system.md:68

Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
```
- `~/Library/LaunchAgents/ai.openclaw.watchdog.plist`
```
quoted
medium Dangerous commands cmd-persistence references/self-healing-system.md:83

Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
```
- `~/Library/LaunchAgents/com.openclaw.healthcheck.plist`
```
quoted
medium Dangerous commands cmd-persistence scripts/gateway-watchdog.sh:41

Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
```
LAUNCHD_PLIST="$HOME/Library/LaunchAgents/ai.openclaw.gateway.plist"
```
code literal
low Exfiltration read-dotenv CONTRIBUTING.md:66

Reads a .env file
```
cp .env.example ~/.openclaw/.env
```
low Exfiltration exfil-webhook-url docs/auto-retry-integration.md:148

Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
```
const WEBHOOK = 'https://discord.com/api/webhooks/.../...';
```
placeholder
low Exfiltration exfil-webhook-url docs/level2-semi-automatic-deployment.md:372

Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
```
export OPENCLAW_DISCORD_WEBHOOK="https://discord.com/api/webhooks/..."
```
placeholder
low Exfiltration exfil-webhook-url docs/LINUX_SETUP.md:91

Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
```
# DISCORD_WEBHOOK_URL="https://discord.com/api/webhooks/..."
```
placeholder
low Exfiltration read-dotenv docs/QUICKSTART.md:78

Reads a .env file
```
cp .env.example ~/.openclaw/.env
```
low Exfiltration exfil-webhook-url docs/QUICKSTART.md:98

Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
```
DISCORD_WEBHOOK_URL="https://discord.com/api/webhooks/YOUR_ID/YOUR_TOKEN"
```
placeholder
low Exfiltration read-dotenv docs/QUICKSTART.md:278

Reads a .env file
```
source ~/.openclaw/.env
```
low Exfiltration read-dotenv docs/QUICKSTART.md:346

Reads a .env file
```
source ~/.openclaw/.env
```
low Exfiltration read-dotenv docs/self-healing-CONTRIBUTING.md:66

Reads a .env file
```
cp .env.example ~/.openclaw/.env
```
low Exfiltration read-dotenv docs/self-healing-QUICKSTART.md:78

Reads a .env file
```
cp .env.example ~/.openclaw/.env
```
low Exfiltration exfil-webhook-url docs/self-healing-QUICKSTART.md:98

Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
```
DISCORD_WEBHOOK_URL="https://discord.com/api/webhooks/YOUR_ID/YOUR_TOKEN"
```
placeholder
low Exfiltration read-dotenv docs/self-healing-QUICKSTART.md:278

Reads a .env file
```
source ~/.openclaw/.env
```
low Exfiltration read-dotenv docs/self-healing-QUICKSTART.md:346

Reads a .env file
```
source ~/.openclaw/.env
```
low Exfiltration read-dotenv docs/self-healing-README.md:121

Reads a .env file
```
cp .env.example ~/.openclaw/.env
```
low Exfiltration exfil-webhook-url docs/self-healing-README.md:255

Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
```
echo 'DISCORD_WEBHOOK_URL="https://discord.com/api/webhooks/..."' >> ~/.openclaw/.env
```
placeholder
low Exfiltration read-dotenv docs/self-healing-TROUBLESHOOTING.md:131

Reads a .env file
```
source ~/.openclaw/.env
```
low Exfiltration read-dotenv docs/self-healing-TROUBLESHOOTING.md:159

Reads a .env file
```
source ~/.openclaw/.env
```
low Exfiltration read-dotenv docs/self-healing-TROUBLESHOOTING.md:319

Reads a .env file
```
source ~/.openclaw/.env
```
low Exfiltration exfil-webhook-url docs/self-healing-TROUBLESHOOTING.md:334

Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
```
DISCORD_WEBHOOK_URL="https://discord.com/api/webhooks/YOUR_ID/YOUR_TOKEN"
```
placeholder
low Exfiltration read-dotenv docs/self-healing-TROUBLESHOOTING.md:443

Reads a .env file
```
cat ~/.openclaw/.env | grep -v '^#' | grep '='
```
low Exfiltration exfil-webhook-url docs/self-improvement-v4-setup.md:210

Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
```
curl -X POST "https://discord.com/api/webhooks/..." \
```
placeholder
low Exfiltration read-dotenv docs/TROUBLESHOOTING.md:131

Reads a .env file
```
source ~/.openclaw/.env
```
low Exfiltration read-dotenv docs/TROUBLESHOOTING.md:159

Reads a .env file
```
source ~/.openclaw/.env
```
low Exfiltration read-dotenv docs/TROUBLESHOOTING.md:319

Reads a .env file
```
source ~/.openclaw/.env
```
low Exfiltration exfil-webhook-url docs/TROUBLESHOOTING.md:334

Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
```
DISCORD_WEBHOOK_URL="https://discord.com/api/webhooks/YOUR_ID/YOUR_TOKEN"
```
placeholder
low Exfiltration read-dotenv docs/TROUBLESHOOTING.md:443

Reads a .env file
```
cat ~/.openclaw/.env | grep -v '^#' | grep '='
```
low Exfiltration exfil-webhook-url docs/v4.0-deployment-report.md:172

Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
```
- URL: `https://discord.com/api/webhooks/1468429341154214049/...`
```
placeholder
low Dangerous commands cmd-pipe-to-shell-known-host install.sh:7

Pipe-to-shell installer from a well-known host (still executes remote code) (code comment)
```
#   curl -sSL https://raw.githubusercontent.com/Ramsbaby/openclaw-self-healing/main/install.sh | bash
```
comment
low Dangerous commands cmd-pipe-to-shell-known-host install.sh:10

Pipe-to-shell installer from a well-known host (still executes remote code) (code comment)
```
#   curl -sSL https://raw.githubusercontent.com/Ramsbaby/openclaw-self-healing/main/install.sh | bash -s -- --workspace ~/my-openclaw
```
comment

low Exfiltration exfil-webhook-url install.sh:204

Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)

$(if [ -n "$discord_webhook" ]; then echo "DISCORD_WEBHOOK_URL=\"$discord_webhook\""; else echo "# DISCORD_WEBHOOK_URL=\"https://discord.com/api/webhooks/...\""; fi)

placeholder

low Exfiltration read-dotenv README.md:285

Reads a .env file
```
cp .env.example ~/.openclaw/.env
```
low Exfiltration exfil-webhook-url README.md:421

Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
```
echo 'DISCORD_WEBHOOK_URL="https://discord.com/api/webhooks/..."' >> ~/.openclaw/.env
```
placeholder
low Dangerous commands cmd-background-process references/LINUX_SETUP.md:40

Starts a background / autostarted process
```
sudo systemctl enable openclaw-gateway
```
low Dangerous commands cmd-background-process references/LINUX_SETUP.md:74

Starts a background / autostarted process
```
sudo systemctl enable openclaw-healthcheck.timer
```
low Exfiltration read-dotenv references/self-healing-TROUBLESHOOTING.md:131

Reads a .env file
```
source ~/.openclaw/.env
```
low Exfiltration read-dotenv references/self-healing-TROUBLESHOOTING.md:159

Reads a .env file
```
source ~/.openclaw/.env
```
low Exfiltration read-dotenv references/self-healing-TROUBLESHOOTING.md:319

Reads a .env file
```
source ~/.openclaw/.env
```
low Exfiltration exfil-webhook-url references/self-healing-TROUBLESHOOTING.md:334

Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
```
DISCORD_WEBHOOK_URL="https://discord.com/api/webhooks/YOUR_ID/YOUR_TOKEN"
```
placeholder
low Exfiltration read-dotenv references/self-healing-TROUBLESHOOTING.md:443

Reads a .env file
```
cat ~/.openclaw/.env | grep -v '^#' | grep '='
```
low Exfiltration exfil-webhook-url scripts/emergency-recovery-v2.sh:105

Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
```
-X POST "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/sendMessage" \
```
placeholder

Files scanned: 41. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

✓ No remarks against the Agent Skills spec

Process rating: all ten parameters 53/100

0Result and completion. Does not say what the result is
0Inputs and preconditions. Does not say what the process needs to start
0Failures and branches. Linear process with no failure handling
0Progress reporting. Says nothing while it works
20When it triggers. No condition that starts the skill
100Tools and files. No external tools needed
100Steps. 12 steps
100Consistency. Name and required fields are in place
100Execution cost. Instruction body is 751 tokens
100Running it twice. No mutating operations

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

+5Description has no quoted example phrases that should trigger the skill
+4Description does not say when NOT to use the skill (false activations)
+3Output format is not stated: the model decides each time
-2localhost URLs: will not work for another user
-35 of 9 scripts are never mentioned in SKILL.md
+1No license
+2Single-language instructions
+3Description length 479: enough signal without eating the budget
+4Structure: 9 headings
+3Step-by-step instructions: 12 items
+4Has examples (3 code blocks)
+4Reference files are cited in the instructions (2 of 26)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.

Tests

— no evals.json

— no spec.yaml

— not run on models

Files · 41

CHANGELOG.md 6K
CONTRIBUTING.md 9K
README.md 20K
SKILL.md 4K
demo-script.sh 3K
docs/DISCORD-FORMATTING-STRATEGY.md 9K
docs/LINUX_SETUP.md 6K
docs/QUICKSTART.md 8K
docs/RECOVERY-SYSTEM-EVALUATION.md 8K
docs/TROUBLESHOOTING.md 12K
docs/auto-retry-integration.md 11K
docs/cron-persona-policy.md 5K
docs/fmp-api-setup.md 1K
docs/level1-rollout-summary.md 8K
docs/level1-tqqq-deployment.md 8K
docs/level2-parameter-tuning-design.md 24K
docs/level2-semi-automatic-deployment.md 11K
docs/realtime-api-setup.md 3K
docs/self-healing-CONTRIBUTING.md 9K
docs/self-healing-QUICKSTART.md 8K
docs/self-healing-README.md 13K
docs/self-healing-TROUBLESHOOTING.md 12K
docs/self-healing-system.md 13K
docs/self-improvement-v4-setup.md 8K
docs/self-review-v5.0.md 8K
docs/system-improvement-plan.md 2K
docs/tqqq-hybrid-monitor-setup.md 5K
docs/v4.0-deployment-report.md 7K
install.sh 18K
references/LINUX_SETUP.md 2K
references/self-healing-TROUBLESHOOTING.md 12K
references/self-healing-system.md 13K
scripts/config-watch.sh 1K
scripts/daily-backup.sh 2K
scripts/emergency-recovery-monitor.sh 5K
scripts/emergency-recovery-v2.sh 17K
scripts/emergency-recovery.sh 13K
scripts/gateway-healthcheck.sh 7K
scripts/gateway-watchdog.sh 31K
scripts/metrics-dashboard.sh 3K
scripts/test-all.sh 3K

Frontmatter

version: 3.1.1

metadata: {"openclaw":{"requires":{"bins":["tmux","claude","jq"]},"install":[{"id":"tmux","kind":"brew","package":"tmux","bins":["

Dates

In catalog since —

Updated in catalog 16 Jun 2026

First seen here 7 Sept 2026

Last analysis 11 Sept 2026, 17:08 UTC

Last seen in crawl 2 d ago

Score history

Date		Score	Safety	Qual.
10 Sept 2026	F	33	0	83
7 Sept 2026	F	32	0	80

Similar skills

B openclaw-self-healing Lord1Egypt/RA-Skills