SKILLEMALL.ai
GitHub ↗ RU Sign in

FD openclaw-maintenance

(no description)

Not recommendedcritical or high security findings · low grade F
ClawHub Agent Skills author: jesson1222-ship-it v0.1.0 12 files · 7 scripts body ≈ 349 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureInfrastructuretype 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
F
0/100
safety, quality, tests
Safety 60%
0
Quality 40%
0
Run on models
none yet
Process rating
D
46/100
Unfinished process
Result and completion w 14
0
When it triggers w 12
0
Inputs and preconditions w 11
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.

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

  1. 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.
  2. Add a description to the frontmatter: without it the skill never triggers.
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 · 26

  • high Dangerous commands cmd-persistence README-proxy-health.md:109
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl unload ~/Library/LaunchAgents/ai.openclaw.proxy-health.plist
  • high Dangerous commands cmd-persistence README-proxy-health.md:112
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load ~/Library/LaunchAgents/ai.openclaw.proxy-health.plist
  • high Dangerous commands cmd-persistence README.md:58
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    ~/Library/LaunchAgents/
  • high Dangerous commands cmd-persistence README.md:63
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load ~/Library/LaunchAgents/ai.openclaw.watchdog.plist
  • high Dangerous commands cmd-persistence README.md:64
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load ~/Library/LaunchAgents/ai.openclaw.proxy-health.plist
  • high Dangerous commands cmd-persistence README.md:74
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl unload ~/Library/LaunchAgents/ai.openclaw.watchdog.plist
  • high Dangerous commands cmd-persistence README.md:75
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl unload ~/Library/LaunchAgents/ai.openclaw.proxy-health.plist
  • high Dangerous commands cmd-persistence SKILL.md:67
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load ~/Library/LaunchAgents/ai.openclaw.watchdog.plist
Medium and low: 18
  • medium Dangerous commands cmd-persistence gateway-watchdog.sh:6
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (code comment)
    # 安装: launchctl load ~/Library/LaunchAgents/ai.openclaw.watchdog.plist
    comment
  • medium Dangerous commands cmd-persistence gateway-watchdog.sh:7
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (code comment)
    # 卸载: launchctl unload ~/Library/LaunchAgents/ai.openclaw.watchdog.plist
    comment
  • medium Dangerous commands cmd-persistence install.sh:32
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    echo "  - launchctl load ~/Library/LaunchAgents/ai.openclaw.watchdog.plist"
    code literal
  • medium Dangerous commands cmd-persistence install.sh:33
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    echo "  - launchctl load ~/Library/LaunchAgents/ai.openclaw.proxy-health.plist"
    code literal
  • medium Dangerous commands cmd-persistence proxy-health.sh:6
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (code comment)
    # 安装: launchctl load ~/Library/LaunchAgents/ai.openclaw.proxy-health.plist
    comment
  • medium Exfiltration net-credential-use proxy-health.sh:98
    Credential used in a network call (verify the destination is the intended service)
    curl -s -m 5 -H "Authorization: Bearer $CLASH_SECRET" \
  • medium Exfiltration net-credential-use proxy-health.sh:139
    Credential used in a network call (verify the destination is the intended service)
    curl -s -m 5 -H "Authorization: Bearer $CLASH_SECRET" \
  • medium Dangerous commands cmd-persistence README-proxy-health.md:12
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation table row)
    | LaunchAgent | `~/Library/LaunchAgents/ai.openclaw.proxy-health.plist` |
    table
  • medium Exfiltration net-credential-use README-proxy-health.md:89
    Credential used in a network call (verify the destination is the intended service)
    curl -H "Authorization: Bearer $CLASH_SECRET" "$CLASH_API/proxies/GLOBAL"
  • medium Exfiltration net-credential-use README-proxy-health.md:92
    Credential used in a network call (verify the destination is the intended service)
    curl -H "Authorization: Bearer $CLASH_SECRET" \
  • medium Exfiltration net-credential-use README-proxy-health.md:96
    Credential used in a network call (verify the destination is the intended service)
    curl -X PUT -H "Authorization: Bearer $CLASH_SECRET" \
  • low Exfiltration read-dotenv AGENT.md:6
    Reads a .env file (security demo / example)
    > 1) 复制环境变量示例：cp .env.example .env
    demo
  • low Exfiltration read-dotenv AGENT.md:18
    Reads a .env file
    cp .env.example .env
  • low Exfiltration read-dotenv install.sh:8
    Reads a .env file (quoted — discussed, not commanded)
    echo "[ERROR] .env not found. Run: cp .env.example .env"
    quoted
  • low Exfiltration read-dotenv README.md:7
    Reads a .env file (security demo / example)
    > 1) 复制环境变量示例：cp .env.example .env
    demo
  • low Dangerous commands cmd-background-process README.md:104
    Starts a background / autostarted process
    sudo systemctl enable --now openclaw-watchdog
  • low Exfiltration read-dotenv SKILL.md:27
    Reads a .env file
    cp .env.example .env
  • low Dangerous commands cmd-background-process SKILL.md:73
    Starts a background / autostarted process
    sudo systemctl enable --now openclaw-watchdog

Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error frontmatter SKILL.md: no YAML frontmatter block found
  • error name-missing SKILL.md: frontmatter has no `name`
  • error description-missing SKILL.md: no `description` — the skill can never trigger

Process rating: all ten parameters 46/100

  • 0Result and completion. Does not say what the result is
  • 0When it triggers. No condition that starts the skill
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 60Tools and files. Uses tools (web) that frontmatter does not declare
  • 100Steps. 17 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 349 tokens
  • 100Running it twice. No mutating operations
  • 100Progress reporting. Reports progress

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 0: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +4Structure: 14 headings
  • +3Step-by-step instructions: 17 items
  • +4Has examples (4 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 0.

External checks

ClawHub: clean
This is a disclosed OpenClaw maintenance skill that can run local monitoring scripts, restart the Gateway, switch proxy nodes, clean logs, and send operational Telegram notifications when the user configures and schedules it.
LLM: benign (high) · VirusTotal: · 29 May 2026