Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 93% confidence
- Finding
- The skill invokes shell scripts and requires command-line tools (`bash`, `curl`, `jq`) but does not declare explicit permissions for shell execution. This creates a trust and containment gap: consumers may treat the skill as lower-risk than it is, while the actual implementation can make outbound network requests and process user-supplied input through a shell wrapper.
