Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 87% confidence
- Finding
- The skill includes executable-style guidance that uses environment variables and shell commands (`process.env`, `npm install`, `npx skills update`) while the skill declares no permissions. That mismatch can mislead an agent runtime or reviewer about the skill's actual capabilities, increasing the chance of unintended secret access or command execution if the skill is trusted and followed automatically.
