Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 88% confidence
- Finding
- The skill invokes shell commands (`bash`, `curl`, `jq`) but does not declare explicit permissions for shell execution, creating a mismatch between stated and actual capabilities. This weakens sandboxing and review controls because a user or platform may underestimate the skill's ability to execute commands and make outbound requests using an API key.
