Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 95% confidence
- Finding
- The skill instructs the agent to read and modify files under `life/areas/**` via a bundled Python script, but it declares no explicit permissions. This creates a permission-model mismatch: an orchestrator or reviewer may treat the skill as lower risk than it really is, while the skill can still drive persistent file reads/writes to a sensitive knowledge base containing personal data.
