Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 70% confidence
- Finding
- Without declared permissions the skill's intent is opaque and cannot be validated.
Security checks across malware telemetry and agentic risk
This skill is a disclosed safety bridge that routes risky external actions through approval checks rather than silently performing them.
Install this only if you intend to use a local or configured action-gate sidecar for risky external actions. Review the endpoint environment variables before use, and treat routed HTTP write requests as potentially high impact because the downstream sidecar or proxy may be able to execute them after approval.
66/66 vendors flagged this skill as clean.