Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 92% confidence
- Finding
- The skill instructs the agent to read JSON and template files, write PDFs/HTML, and use a Python environment, but it declares no permissions. This mismatch is a real security issue because it hides the skill's actual capabilities from any permission or policy layer and can lead to unintended file access or modification within the workspace.
