Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 95% confidence
- Finding
- The skill clearly documents shell-capable behavior via Node.js, ffmpeg, and Whisper invocation, yet it declares no corresponding permissions or execution capabilities. This creates a transparency and policy gap: users or orchestration layers may underestimate that the skill can execute local commands and process local files, which increases the risk of unsafe invocation or insufficient sandboxing.
