Caveat verdict

simmer-skill-builder

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

A meta-skill that generates trading skill code from natural language descriptions for the Simmer prediction market platform, with no network calls, no credential access, and behavior consistent with skill-building.

⚠ 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.

0
security
90
transparency
70
maintenance

Findings (5)

Pattern match critical

<script> tag in markdown — potential code injection

SKILL.md · code · <script>

Pattern match critical

Possible hardcoded credential

references/simmer-api.md · code · api_key="sk_live_...

Pattern match high

Writes to SKILL.md — self-modifying skill

SKILL.md · prose · downgraded · SKILL.md you generate (everything after the closing `---`) is rendered as the pr

Pattern match medium

Python urllib.request — network access

references/skill-template.md · code · urllib.request

Pattern match medium

Python os.environ.get — reads environment variable

references/skill-template.md · code · os.environ.get(

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