Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 86% confidence
- Finding
- The skill explicitly instructs the agent to call external APIs and references executable scripts/API docs, which implies network and possibly environment-backed execution capabilities, yet no permissions are declared. This creates a transparency and policy-enforcement gap: a host may invoke the skill without understanding that it can trigger outbound requests or rely on sensitive runtime configuration such as API keys.
