Caveat verdict
self-improvement
hi
Self-improvement logging skill recording errors and corrections to local markdown files; memory writes stay within the workspace with no external 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.
Permission integrity
agent_memory
Findings (6)
Possible hardcoded credential
README.md · code · API_KEY="sk-or-v1-...
References agent configuration files
references/examples.md · code · CLAUDE.md
References agent memory files
SKILL.md · code · MEMORY.md
Popular HTTP library — network access
README.md · code · got
Accesses OpenClaw config/secrets directly
skill.json · prose · downgraded · ~/.openclaw/openclaw.json
Python os.environ.get — reads environment variable
main.py · prose · downgraded · os.environ.get(
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.
agent_memory Is this flag fair?
Thanks — recorded.