Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 92% confidence
- Finding
- The skill invokes a shell script and instructs users to provide secrets via environment variables, but it does not declare any permissions. Undeclared shell capability weakens security review and consent boundaries because the skill can perform networked actions and process user-supplied input without an explicit permission model, increasing the chance of misuse or command-handling bugs in the referenced script.
