Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 93% confidence
- Finding
- The skill documentation indicates capabilities consistent with shell execution and file writing via ffmpeg usage, but it does not declare any permissions or safety boundaries. This creates a trust and review gap: downstream systems or users may invoke a skill that can write files and spawn shell-backed processing without explicit acknowledgment, increasing the risk of command injection or unsafe file operations in the implementation.
