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 local reporting tool for GitHub Actions failure exports, with no evidence of hidden network access, persistence, or destructive behavior.
Use this only on GitHub Actions exports you are comfortable analyzing locally. Scope the GitHub CLI export and RUN_GLOB narrowly, and avoid sharing raw output if it contains private repo names, branch names, actor identities, workflow details, or run URLs. Verify the package version if you need the 1.2.0 filter features described in metadata.
66/66 vendors flagged this skill as clean.