Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 88% confidence
- Finding
- The skill explicitly instructs the agent to verify files, execute sub-skills, append audit logs, and produce reproducibility artifacts, which implies file-write capability and likely external/networked operations, yet no permissions are declared. This mismatch can cause the platform or user to underestimate what the skill may do, weakening security review and consent boundaries.
