Caveat verdict
skill-evolve-pro
Skill evolution engine analyzing failure trajectories and calling DeepSeek API for error classification; requires explicit user confirmation before applying any changes with diff review gate.
⚠ 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.
Findings (4)
Possible hardcoded credential
README.md · code · API_KEY = "sk-your-key-here
Python os.environ.get — reads environment variable
README.md · code · os.environ.get(
Python urllib.request — network access
scripts/evolve_core.py · prose · downgraded · urllib.request
References agent memory files
scripts/skill_apply.py · prose · downgraded · MEMORY.md
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.