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 is a local fine-tuning plan generator with ordinary file input and output behavior, plus a dry-run labeling caveat.
Install only if you are comfortable running a local Python script. Use a non-sensitive JSON input file and choose a disposable output path; do not rely on --dry-run to prevent file creation or overwrites.
66/66 vendors flagged this skill as clean.