Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 86% confidence
- Finding
- The skill advertises executable scripts that read environment variables, read and write workspace files, and likely interact with MCP-like capabilities, but it declares no permissions or equivalent capability boundaries. This creates a transparency and policy-enforcement gap: a caller or platform may treat the skill as lower risk than it is, while the documented commands clearly persist state and inspect environment-driven paths.
