Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 84% confidence
- Finding
- The skill documentation instructs use of shell commands and access to local secret files, but no explicit permissions are declared. That creates a trust gap: an agent or reviewer may not realize the skill can read sensitive files like the age key and encrypted env file and invoke local commands to process them. In this context the capability is expected for the stated purpose, but the lack of declaration still increases the risk of unintended secret access or execution beyond what users consented to.
