Caveat verdict
mcp-best-practices
Reference documentation for MCP TypeScript SDK best practices; content is purely informational with no suspicious behavior.
⚠ 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.
Findings (6)
<script> tag in markdown — potential code injection
references/mcp-apps.md · code · <script
Recursive delete from root or home — destructive command
references/security-auth.md · code · rm -rf /
Instructs covert action — may act without user awareness
SKILL.md · code · silently
References sudo — requests elevated privileges
references/security-auth.md · code · sudo
Accesses .ssh directory
references/security-auth.md · code · .ssh/
Opens WebSocket connection
SKILL.md · prose · downgraded · WebSocket
Permissions & capabilities
No declared permissions — minimal attack surface.
network_in Is this flag fair?
Thanks — recorded.