Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 86% confidence
- Finding
- The skill performs sensitive actions (reading an API key from the environment, making outbound network requests, and explicitly stating results may be saved to the working directory) but does not declare corresponding permissions. This creates a transparency and governance gap: an agent or reviewer may not realize the skill can exfiltrate user queries to an external service or write retrieved data locally.
