Caveat verdict

skill-atlas

windcat-skill-atlas

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Skill management tool for tracking and organizing installed skills; file read and process exec capabilities are used legitimately for skill lifecycle management.

⚠ 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.

28
security
80
transparency
90
maintenance

Findings (6)

Pattern match high

Accesses cloud provider credentials

reference.md · code · ~/.aws

Pattern match high

Uses eval() — can execute arbitrary code

reference.md · prose · downgraded · eval(

Pattern match medium

Python shutil file operation — copies/moves/deletes files

SKILL.md · code · shutil.copytree(

Pattern match medium

Uses exec() — may execute shell commands

reference.md · prose · downgraded · exec(

Pattern match medium

References sudo — requests elevated privileges

reference.md · prose · downgraded · sudo

Pattern match low

References agent memory files

reference.md · prose · downgraded · MEMORY.md

Permissions & capabilities

No declared permissions — minimal attack surface.

file_readprocess_exec

Is this flag fair?

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