Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 89% confidence
- Finding
- The skill invokes shell-style commands and relies on environment variables for authentication, but it does not declare permissions reflecting those capabilities. This creates a transparency and consent gap: users and hosting platforms may not realize the skill can access secrets and initiate outbound requests, increasing the risk of unintended secret exposure or over-privileged execution.
