ClawAudit verdict

self-improving-agent

self-improvement-agent

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

The skill seems to be a genuine improvement agent, capturing learnings and errors for continuous improvement, with no obvious malicious intent.

⚠ 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.

75
security
70
transparency
70
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (2)

Pattern match medium

References agent configuration files

references/examples.md · code · CLAUDE.md

Pattern match medium

References agent memory files

references/openclaw-integration.md · code · MEMORY.md

Why the tier is capped

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

package_install

Is this flag fair?

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