Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 95% confidence
- Finding
- The skill documentation instructs the agent to run Python scripts that perform network access, invoke shell commands, and optionally install dependencies, yet the skill declares no permissions for those capabilities. This creates a transparency and policy-enforcement gap: an agent or reviewer may treat the skill as lower risk than it is, while the skill can still fetch remote code/data and execute commands that affect the local environment.
