ClawAudit verdict

self-improving-skill

jz-self-improving-skill

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

The skill automates diffing AI drafts vs. human edits and updating local SKILL.md files; all file operations and script executions are local and serve the stated self-improvement purpose with no external data transmission detected.

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

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

88
security
80
transparency
90
maintenance

Permission integrity

Accesses agent memory/configuration files

agent_memory

Findings (2)

Pattern match medium

subprocess execution — runs system commands from Python

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

Pattern match low

Python os.environ.get — reads environment variable

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

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class 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.

agent_memory

Is this flag fair?

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