Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 95% confidence
- Finding
- The skill documentation describes use of shell commands, network access, and repository/file operations, but there is no declared permissions model or explicit scoping of those capabilities. In an agent setting, this can lead to over-privileged execution where the agent can clone arbitrary repositories, invoke authenticated CLIs, and modify remote state without clear user consent boundaries.
