Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 89% confidence
- Finding
- The skill instructs the agent to read an API token from the environment and make outbound network requests, but it declares no permissions. This creates a permission-model mismatch: a user or platform may not realize the skill can access local secrets and transmit data externally, which increases the risk of unintended secret use or exfiltration if the skill is reused, modified, or invoked in broader contexts.
