Caveat verdict

expert-mode

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

The skill downloads agent persona configurations from multiple GitHub repositories and writes them to MEMORY.md to alter the agent's persistent behavior; while it includes a content-review step, the pattern of fetching external instructions and writing them to agent memory is an elevated supply-chain risk.

⚠ 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.

60
security
60
transparency
70
maintenance

Permission integrity

Accesses agent memory/configuration files

agent_memory

Findings (2)

Pattern match critical

<script> tag in markdown — potential code injection

SKILL.md · code · <script>

Pattern match medium

References agent memory files

SKILL.md · code · MEMORY.md

Permissions & capabilities

No declared permissions — minimal attack surface.

dynamic_evalagent_memory

Is this flag fair?

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