Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 94% confidence
- Finding
- The skill explicitly expects shell execution, environment variable access, and local file reads/writes, but it does not declare permissions in a machine-enforceable way. That mismatch is a real security issue because an agent platform may grant or evaluate capabilities incorrectly, reducing transparency and weakening policy enforcement for a skill that can run commands and manipulate local data.
