Caveat verdict

complisec

eu-compliance

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

This skill enforces EU compliance rules by reading a local profile file and applying enforcement logic during agent sessions; it performs no network calls, accesses no secrets, and its behavior is entirely transparent and user-directed.

⚠ 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.

20
security
70
transparency
70
maintenance

Findings (4)

Pattern match high

Writes to SKILL.md — self-modifying skill

SKILL.md · prose · downgraded · SKILL.md` | Write

Pattern match high

Pipe to python — executes piped content as Python code

skills/audit-logging/references/logging-guide.md · prose · downgraded · | Python

Pattern match high

Possible hardcoded credential

skills/data-sensitivity/references/pattern-index.md · prose · downgraded · api_key = "sk-abc123...

Pattern match high

Attempts to modify skills or system prompts

USE-CASES.md · prose · downgraded · modify SKILL.md

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