Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 90% confidence
- Finding
- The skill documentation advertises executable capabilities that require network access and shell execution, but no permissions are declared. This creates a transparency and policy-enforcement gap: an agent or reviewer may underestimate what the skill can do, while the runtime may still perform external requests and process execution. In this context the functionality is expected for stock lookup, but undeclared capabilities still increase risk because they enable outbound access and command execution without explicit scoping.
