Caveat verdict

skill-sediment

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

A plugin installer that deploys a TypeScript OpenClaw plugin from locally bundled assets to auto-generate SKILL.md files from successful conversations; all operations are local with no external data exfiltration.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

0
security
70
transparency
70
maintenance

Findings (21)

Pattern match high

Pipe to python — executes piped content as Python code

assets/plugin-source/src/skills-guard.ts · prose · downgraded · |python

Pattern match high

Uses eval() — can execute arbitrary code

assets/plugin-source/src/skills-guard.ts · prose · downgraded · eval(

Pattern match high

Pipe to sh — executes piped content as shell commands

assets/plugin-source/src/skills-guard.ts · prose · downgraded · |sh

Pattern match medium

Accesses OpenClaw config/secrets directly

README.md · prose · downgraded · ~/.openclaw/openclaw.json

Pattern match medium

Accesses .ssh directory

assets/plugin-source/src/skills-guard.ts · prose · downgraded · .ssh/

Pattern match medium

References SSH/GPG private keys

assets/plugin-source/src/skills-guard.ts · prose · downgraded · ssh-key

Pattern match medium

Uses exec() — may execute shell commands

assets/plugin-source/src/skills-guard.ts · prose · downgraded · exec(

Pattern match medium

References child_process — can spawn system processes

assets/plugin-source/src/skills-guard.ts · prose · downgraded · child_process

Pattern match medium

os.system/popen — direct OS command execution

assets/plugin-source/src/skills-guard.ts · prose · downgraded · os.system(

Pattern match medium

References sudo — requests elevated privileges

assets/plugin-source/src/skills-guard.ts · prose · downgraded · sudo

Pattern match medium

setuid — privilege escalation mechanism

assets/plugin-source/src/skills-guard.ts · prose · downgraded · setuid

Pattern match medium

Instructs covert action — may act without user awareness

references/sediment-internals.md · prose · downgraded · silently

Pattern match medium

subprocess execution — runs system commands from Python

scripts/manage.py · prose · downgraded · subprocess.run(

Pattern match low

References agent configuration files

assets/plugin-source/src/auto-review.ts · prose · downgraded · AgentConfig

Pattern match low

Python os.getenv — reads environment variable

assets/plugin-source/src/skills-guard.ts · prose · downgraded · os.getenv(

Pattern match low

References tunneling service

assets/plugin-source/src/skills-guard.ts · prose · downgraded · ngrok

Pattern match low

Base64 encoding/decoding

assets/plugin-source/src/skills-guard.ts · prose · downgraded · base64_decode

Pattern match low

Python urllib.request — network access

scripts/manage.py · prose · downgraded · urllib.request

Pattern match low

Python os.environ.get — reads environment variable

scripts/manage.py · prose · downgraded · os.environ.get(

Pattern match low

Popular HTTP library — network access

scripts/manage.py · prose · downgraded · got

Pattern match low

Python shutil file operation — copies/moves/deletes files

scripts/manage.py · prose · downgraded · shutil.copy(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API