Caveat verdict

self-evolving-agent

self-evo-agent

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

The skill builds a goal-driven self-learning loop for OpenClaw and coding agents, which might pose risks due to its autonomous nature and potential for unintended behavior.

⚠ 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.

75
security
90
transparency
70
maintenance

Findings (4)

Pattern match medium

References agent memory files

install.md · code · MEMORY.md

Pattern match medium

subprocess execution — runs system commands from Python

scripts/run-benchmark.py · prose · downgraded · subprocess.run(

Pattern match low

Python os.environ.get — reads environment variable

scripts/run-benchmark.py · prose · downgraded · os.environ.get(

Pattern match low

Popular HTTP library — network access

scripts/run-evals.py · prose · downgraded · got

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.

Is this flag fair?

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