Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 86% confidence
- Finding
- The skill declares runtime requirements for an environment variable API key and documents a backend HTTPS API endpoint, but it does not declare explicit permissions corresponding to those capabilities. This creates a trust and containment gap: an agent or platform may execute code with network access and secret access that are not transparently represented in the skill's permission model, increasing the risk of unintended data exfiltration or misuse if the referenced script behaves unexpectedly.
