Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 85% confidence
- Finding
- The skill invokes shell scripts and makes outbound API calls, but the manifest does not declare explicit permissions for shell or network access. This creates a transparency and policy-enforcement gap: a host system or reviewer may underestimate the skill’s capabilities, and future permission gating cannot reliably restrict it. In this context the behavior is expected for the skill’s purpose, but undeclared capabilities are still a real security weakness.
