Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 94% confidence
- Finding
- The skill instructs the agent to run a Python script that uses an environment variable API key and performs external network access, yet the skill declares only metadata requirements instead of explicit permissions. This creates a trust gap: an agent or reviewer may underestimate the skill's ability to access secrets and send data off-box, increasing the risk of unintended secret exposure or unauthorized network operations.
