Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 94% confidence
- Finding
- The skill explicitly instructs use of a shell helper script but does not declare any tool restrictions or allowed-tools scope. That creates an avoidable over-permission risk: an agent may be allowed broader shell execution than necessary, and later edits or prompt injection through skill inputs could leverage that capability beyond the intended API calls.
