FC openclaw-security-monitor

Proactive security monitoring, threat scanning, and auto-remediation for OpenClaw deployments

Not recommendedcritical or high security findings · low grade F

modbender/skill-library-mcp Agent Skills author: modbender MIT 58 files · 48 scripts body ≈ 2 686 tokens Open the sourcegithub.com↗ analyzed 3 d ago

Proactive security monitoring, threat scanning, and auto-remediation for OpenClaw deployments

As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches

Procedure Telegram GitHub VS Code Docker Infrastructure Data and analyticstype 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

27/100

safety, quality, tests

Safety 60%: 0
Quality 40%: 68
Run on models: none yet

Process rating

51/100

Has gaps

Result and completion w 14: 0
Failures and branches w 10: 0
When it triggers w 12: 20

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.

Risky intent medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.

For the author

Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

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.
Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.

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 · 65

high Dangerous commands cmd-persistence scripts/dashboard.sh:166

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
CRON_EXISTS=$(crontab -l 2>/dev/null | grep -c "$SELF_DIR_NAME" || true)
```

Medium and low: 64

medium Dangerous commands cmd-persistence README.md:164

Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
```
ls ~/Library/LaunchAgents/ | grep -ivE "com\.apple|com\.openclaw\.security"
```
security skill
medium Dangerous commands cmd-persistence README.md:619

Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
```
ls -la ~/Library/LaunchAgents/ | grep -iE "openclaw|clawdbot|moltbot"
```
security skill
medium Dangerous commands cmd-persistence README.md:621

Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
```
launchctl unload ~/Library/LaunchAgents/<suspicious-plist>
```
security skill
medium Dangerous commands cmd-persistence README.md:622

Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
```
rm ~/Library/LaunchAgents/<suspicious-plist>
```
security skill
medium Dangerous commands cmd-privilege scripts/remediate/check-04-exfil-endpoints.sh:118

Privilege escalation / world-writable permissions
```
sudo cp /etc/hosts "$HOSTS_BACKUP"
```
medium Risky intent intent-wallet-secrets scripts/remediate/check-05-crypto-wallet.sh:73

Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
```
a) Transfer funds to a NEW wallet with a NEW seed phrase:
```
medium Risky intent intent-wallet-secrets scripts/remediate/check-05-crypto-wallet.sh:74

Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
```
- Create new wallet with fresh seed phrase
```
medium Risky intent intent-wallet-secrets scripts/remediate/check-05-crypto-wallet.sh:76

Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
```
- Never reuse the old seed phrase
```
medium Dangerous commands cmd-pipe-to-shell scripts/remediate/check-06-curl-pipe.sh:78

Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)
```
"curl | sh" and similar patterns are extremely dangerous as they:
```
code literal
medium Exfiltration exfil-read-secret-files scripts/remediate/check-16-env-leakage.sh:11

Reads credential / secret files (quoted — discussed, not commanded)
```
"cat.*\.aws/credentials"
```
quoted
medium Dangerous commands cmd-persistence scripts/remediate/check-22-persistence.sh:5

Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
```
log "Check 22: Audit/remove unauthorized LaunchAgents/crontabs"
```
code literal
medium Dangerous commands cmd-persistence scripts/scan.sh:643

Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
```
CRON_ENTRIES=$(crontab -l 2>/dev/null | grep -ivE "${SELF_DIR_NAME}|#" | grep -iE "openclaw|clawdbot|moltbot|curl.*\|.*sh|wget.*\|.*bash" || true)
```
security skill
medium Exfiltration net-credential-use scripts/telegram-setup.sh:24

Credential used in a network call (verify the destination is the intended service)
```
UPDATES=$(curl -s "https://api.telegram.org/bot${TELEGRAM_TOKEN}/getUpdates?limit=5" --connect-timeout 10 2>/dev/null)
```
medium Exfiltration net-credential-use scripts/telegram-setup.sh:37

Credential used in a network call (verify the destination is the intended service)
```
RESULT=$(curl -s -X POST "https://api.telegram.org/bot${TELEGRAM_TOKEN}/sendMessage" \
```
medium Dangerous commands cmd-persistence SKILL.md:125

Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
```
launchctl unload ~/Library/LaunchAgents/com.openclaw.security-dashboard.plist
```
security skill
medium Dangerous commands cmd-persistence SKILL.md:126

Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
```
launchctl load ~/Library/LaunchAgents/com.openclaw.security-dashboard.plist
```
security skill
low Risky intent intent-offensive-security docs/threat-model.md:57

Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
```
### 5. Credential Harvesting
```
low Risky intent intent-offensive-security docs/threat-model.md:184

Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
```
| GHSA-v773-* | Slack dmPolicy=open privilege escalation | Medium | v2026.2.14 |
```
low Risky intent intent-offensive-security ioc/c2-ips.txt:13

Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
```
# Reverse shell endpoint
```
low Risky intent intent-offensive-security ioc/c2-ips.txt:14

Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
```
54.91.154.110|clawhavoc-revshell|2026-01-28|Reverse shell target port 13338
```
low Risky intent intent-offensive-security ioc/malicious-domains.txt:15

Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
```
burpcollaborator.net|exfil|generic|Pentest tool (suspicious in skills)
```
low Risky intent intent-offensive-security ioc/malicious-skill-patterns.txt:47

Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
```
^polymarket-all-in-one$|reverse-shell|Contains reverse shell backdoor (noreplyboter)
```
low Dangerous commands cmd-cron-mention README.md:50

Mentions editing / listing crontab (documentation of a security skill)
```
crontab -l | { cat; echo "0 6 * * * $(pwd)/scripts/daily-scan-cron.sh"; } | crontab -
```
security skill
low Risky intent intent-offensive-security README.md:179

Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
```
**What it means:** A skill contains reverse shell patterns (`nc -e`, `/dev/tcp/`, `socat exec`, etc.) or Gatekeeper bypass commands (`xattr -cr`).
```
low Dangerous commands cmd-privilege README.md:213

Privilege escalation / world-writable permissions (documentation of a security skill)
```
sudo sh -c 'echo "127.0.0.1 webhook.site" >> /etc/hosts'
```
security skill
low Dangerous commands cmd-privilege README.md:214

Privilege escalation / world-writable permissions (documentation of a security skill)
```
sudo sh -c 'echo "127.0.0.1 pipedream.net" >> /etc/hosts'
```
security skill
low Dangerous commands cmd-privilege README.md:215

Privilege escalation / world-writable permissions (documentation of a security skill)
```
sudo sh -c 'echo "127.0.0.1 hookbin.com" >> /etc/hosts'
```
security skill
low Dangerous commands cmd-privilege README.md:216

Privilege escalation / world-writable permissions (documentation of a security skill)
```
sudo sh -c 'echo "127.0.0.1 requestbin.com" >> /etc/hosts'
```
security skill
low Dangerous commands cmd-shell-rc README.md:283

Writes to a shell startup file (documentation of a security skill)
```
echo 'umask 077' >> ~/.zshrc
```
security skill
low Dangerous commands cmd-cron-mention README.md:633

Mentions editing / listing crontab (documentation of a security skill)
```
crontab -l | grep -iE "openclaw|clawdbot|moltbot"
```
security skill
low Dangerous commands cmd-cron-mention README.md:635

Mentions editing / listing crontab (documentation of a security skill)
```
crontab -e
```
security skill
low Dangerous commands cmd-privilege README.md:680

Privilege escalation / world-writable permissions (documentation of a security skill)
```
sudo sh -c 'echo "$HOME/.openclaw/logs/*.log 640 7 1000 * J" >> /etc/newsyslog.conf'
```
security skill

low Risky intent intent-offensive-security README.md:721

Offensive-security / dual-use content (legitimate for authorised testing; review intended use)

**What it means:** The `exec-approvals.json` allows remote command execution without confirmation. The CVE-…253 exploit chain used `exec.approvals.set` to disable confirmation prompts.

low Dangerous commands cmd-pipe-to-shell-known-host README.md:780

Pipe-to-shell installer from a well-known host (still executes remote code) (documentation of a security skill)
```
curl -fsSL https://deb.nodesource.com/setup_22.x | sudo bash -
```
security skill
low Risky intent intent-offensive-security README.md:974

Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
```
| `54.91.154.110` | ClawHavoc | Reverse shell endpoint (port 13338) |
```
low Risky intent intent-offensive-security README.md:1109

Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
```
| CVE-…763 | Command injection | #3: Reverse shell patterns |
```
detector
low Risky intent intent-offensive-security README.md:1128

Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
```
| [SOCRadar](https://socradar.io/blog/cve-…ken/) | CVE-…253 Analysis | Exploit chain technical details |
```
low Dangerous commands cmd-pipe-to-shell-known-host README.md:1259

Pipe-to-shell installer from a well-known host (still executes remote code) (documentation of a security skill)
```
curl -fsSL https://deb.nodesource.com/setup_22.x | sudo bash -
```
security skill
low Exfiltration exfil-webhook-url scripts/daily-scan-cron.sh:57

Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
```
curl -s -X POST "https://api.telegram.org/bot${TELEGRAM_TOKEN}/sendMessage" \
```
placeholder
low Exfiltration net-credential-use scripts/daily-scan-cron.sh:57

Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)
```
curl -s -X POST "https://api.telegram.org/bot${TELEGRAM_TOKEN}/sendMessage" \
```
security skill
low Exfiltration exfil-webhook-url scripts/daily-scan-cron.sh:84

Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
```
UPDATES=$(curl -s "https://api.telegram.org/bot${TELEGRAM_TOKEN}/getUpdates?limit=5" --connect-timeout 10 2>/dev/null)
```
placeholder
low Exfiltration net-credential-use scripts/daily-scan-cron.sh:84

Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)
```
UPDATES=$(curl -s "https://api.telegram.org/bot${TELEGRAM_TOKEN}/getUpdates?limit=5" --connect-timeout 10 2>/dev/null)
```
security skill
low Dangerous commands cmd-cron-mention scripts/dashboard.sh:166

Mentions editing / listing crontab
```
CRON_EXISTS=$(crontab -l 2>/dev/null | grep -c "$SELF_DIR_NAME" || true)
```
low Dangerous commands cmd-cron-mention scripts/remediate/check-03-reverse-shells.sh:91

Mentions editing / listing crontab
```
crontab -l
```
low Dangerous commands cmd-privilege scripts/remediate/check-04-exfil-endpoints.sh:122

Privilege escalation / world-writable permissions (detector / deny-list definition; code comment)
```
echo "127.0.0.1 $domain # Blocked by openclaw-security-monitor" | sudo tee -a /etc/hosts > /dev/null
```
detectorcomment
low Dangerous commands cmd-cron-mention scripts/remediate/check-22-persistence.sh:35

Mentions editing / listing crontab
```
if crontab -l &>/dev/null; then
```
low Dangerous commands cmd-cron-mention scripts/remediate/check-22-persistence.sh:38

Mentions editing / listing crontab
```
crontab -l | while IFS= read -r line; do
```
low Dangerous commands cmd-cron-mention scripts/remediate/check-22-persistence.sh:52

Mentions editing / listing crontab (detector / deny-list definition; string literal in code, not executed)
```
guidance "  crontab -e"
```
detectorcode literal
low Dangerous commands cmd-privilege scripts/remediate/check-22-persistence.sh:70

Privilege escalation / world-writable permissions (string literal in code, not executed)
```
guidance "  sudo rm \"$plist\""
```
code literal
low Dangerous commands cmd-pipe-to-shell-known-host scripts/remediate/check-28-nodejs-cve.sh:59

Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed)
```
"   curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash" \
```
code literal
low Dangerous commands cmd-background-process scripts/remediate/check-31-internet-expose.sh:157

Starts a background / autostarted process (string literal in code, not executed)
```
"   sudo systemctl enable iptables" \
```
code literal
low Dangerous commands cmd-background-process scripts/remediate/check-31-internet-expose.sh:158

Starts a background / autostarted process (string literal in code, not executed)
```
"   sudo systemctl enable ip6tables"
```
code literal

low Dangerous commands cmd-cron-mention scripts/scan.sh:643

Mentions editing / listing crontab (documentation of a security skill)

CRON_ENTRIES=$(crontab -l 2>/dev/null | grep -ivE "${SELF_DIR_NAME}|#" | grep -iE "openclaw|clawdbot|moltbot|curl.*\|.*sh|wget.*\|.*bash" || true)

security skill

low Exfiltration exfil-webhook-url scripts/telegram-setup.sh:24

Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
```
UPDATES=$(curl -s "https://api.telegram.org/bot${TELEGRAM_TOKEN}/getUpdates?limit=5" --connect-timeout 10 2>/dev/null)
```
placeholder
low Exfiltration exfil-webhook-url scripts/telegram-setup.sh:37

Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
```
RESULT=$(curl -s -X POST "https://api.telegram.org/bot${TELEGRAM_TOKEN}/sendMessage" \
```
placeholder
low Risky intent intent-offensive-security SKILL.md:45

Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
```
26. Exec-approvals configuration audit (CVE-…253 exploit chain)
```
low Dangerous commands cmd-cron-mention SKILL.md:142

Mentions editing / listing crontab (documentation of a security skill)
```
crontab -l | { cat; echo "0 6 * * * $HOME/.openclaw/workspace/skills/<skill-dir>/scripts/daily-scan-cron.sh"; } | crontab -
```
security skill

A further 7 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 58. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 51/100

0Result and completion. Does not say what the result is
0Failures and branches. Linear process with no failure handling
20When it triggers. No condition that starts the skill
30Running it twice. 4 mutating operations with no state check
60Tools and files. Uses tools (bash, web) that frontmatter does not declare
70Inputs and preconditions. Inputs and preconditions are listed
85Steps. 69 steps, 3 vague phrases
100Consistency. Name and required fields are in place
100Execution cost. Instruction body is 2686 tokens
100Progress reporting. Reports progress

medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

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)
+3Description length 93: 120–800 characters recommended
+3Output format is not stated: the model decides each time
-41 reference files, but SKILL.md never points to them: the model will not open them
+1No license
+2Single-language instructions
+4Structure: 14 headings
+3Step-by-step instructions: 69 items
+4Has examples (8 code blocks)
+3All 7 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.

Tests

— no evals.json

— no spec.yaml

— not run on models

Files · 58

README.md 57K
SKILL.md 11K
dashboard/index.html 29K
dashboard/server.js 15K
docs/threat-model.md 16K
ioc/c2-ips.txt 1K
ioc/file-hashes.txt 1K
ioc/malicious-domains.txt 2K
ioc/malicious-publishers.txt 2K
ioc/malicious-skill-patterns.txt 3K
scripts/daily-scan-cron.sh 3K
scripts/dashboard.sh 6K
scripts/network-check.sh 3K
scripts/remediate/_common.sh 3K
scripts/remediate/check-01-c2-ips.sh 2K
scripts/remediate/check-02-amos-stealer.sh 3K
scripts/remediate/check-03-reverse-shells.sh 3K
scripts/remediate/check-04-exfil-endpoints.sh 4K
scripts/remediate/check-05-crypto-wallet.sh 3K
scripts/remediate/check-06-curl-pipe.sh 4K
scripts/remediate/check-07-file-perms.sh 3K
scripts/remediate/check-08-skill-integrity.sh 5K
scripts/remediate/check-09-skillmd-inject.sh 2K
scripts/remediate/check-10-memory-poison.sh 3K
scripts/remediate/check-11-base64-obfusc.sh 3K
scripts/remediate/check-12-binary-dl.sh 3K
scripts/remediate/check-13-gateway-config.sh 3K
scripts/remediate/check-14-websocket-sec.sh 2K
scripts/remediate/check-15-malicious-pub.sh 3K
scripts/remediate/check-16-env-leakage.sh 4K
scripts/remediate/check-17-dm-policy.sh 2K
scripts/remediate/check-18-tool-policy.sh 2K
scripts/remediate/check-19-sandbox-config.sh 2K
scripts/remediate/check-20-mdns-exposure.sh 1K
scripts/remediate/check-21-session-perms.sh 2K
scripts/remediate/check-22-persistence.sh 3K
scripts/remediate/check-23-plugin-audit.sh 2K
scripts/remediate/check-24-log-redaction.sh 3K
scripts/remediate/check-25-proxy-bypass.sh 2K
scripts/remediate/check-26-exec-approvals.sh 2K
scripts/remediate/check-27-docker-sec.sh 3K
scripts/remediate/check-28-nodejs-cve.sh 3K
scripts/remediate/check-29-plaintext-creds.sh 4K
scripts/remediate/check-30-vscode-trojans.sh 3K
scripts/remediate/check-31-internet-expose.sh 7K
scripts/remediate/check-32-mcp-security.sh 6K
scripts/remediate/check-33-clawjacked.sh 3K
scripts/remediate/check-34-ssrf.sh 3K
scripts/remediate/check-35-safebins.sh 2K
scripts/remediate/check-36-acp-approval.sh 2K
scripts/remediate/check-37-path-hijack.sh 2K
scripts/remediate/check-38-env-override.sh 2K
scripts/remediate/check-39-deeplink.sh 2K
scripts/remediate/check-40-log-poisoning.sh 4K
scripts/remediate.sh 8K
scripts/scan.sh 58K
scripts/telegram-setup.sh 2K
scripts/update-ioc.sh 7K

Frontmatter

tags: ["security","scan","remediation","monitoring","threat-detection","hardening"]

version: 3.4.0

author: Adrian Birzu

user-invocable: true

Dates

In catalog since —

Updated in catalog 16 Jun 2026

First seen here 7 Sept 2026

Last analysis 11 Sept 2026, 17:01 UTC

Last seen in crawl 36 h ago

Score history

Date		Score	Safety	Qual.
7 Sept 2026	F	27	0	68
7 Sept 2026	F	25	0	62