Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 88% confidence
- Finding
- The skill explicitly instructs use of shell commands via curl, but no corresponding permissions are declared. This creates a mismatch between the skill's documented capabilities and its declared security model, making external network actions harder to review and govern. In an agent environment, undeclared shell/network use increases the chance of unvetted command execution and data handling.
