Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 84% confidence
- Finding
- The skill advertises and instructs use of sensitive environment variables, shell execution, network access, and local script invocation, but does not declare corresponding permissions. This creates a transparency and trust problem: an agent or user may approve the skill assuming minimal privileges, while the documented workflow clearly enables credential handling and outbound requests to a third-party service.
