Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 95% confidence
- Finding
- The skill instructs the agent to use environment variables, read and write local files, and access remote services, yet it declares no permissions. This creates a dangerous mismatch between the skill's apparent trust boundary and its actual capabilities, increasing the risk of unauthorized file modification, secret exposure, or unintended network access during execution.
