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 locally reviews a fixed set of workspace markdown files and creates a report, with cleanup edits explicitly requiring user approval.
Install only if you are comfortable with the skill reading the listed durable workspace files. Review the generated report before acting, and approve deletions or edits only after checking the specific content proposed for removal.
66/66 vendors flagged this skill as clean.