Caveat verdict
Smith Matrix
smith-matrix
45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.
The skill manages agent memory for a multi-agent system, which could potentially be used for unauthorized access or manipulation.
⚠ 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.
80
security
100
transparency
90
maintenance
Permission integrity
Accesses agent memory/configuration files
agent_memory
Findings (1)
Pattern match high
<script> tag in markdown — potential code injection
examples/code-refactor.md · prose · downgraded · <script>
Permissions & capabilities
No declared permissions — minimal attack surface.
agent_memory Is this flag fair?
Thanks — recorded.