Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 94% confidence
- Finding
- The skill explicitly directs the agent to run a live trading bot that uses network access and likely environment-based secrets, yet it declares no permissions. This creates a dangerous mismatch between the skill's documented behavior and its security model, making it easier for an agent or reviewer to approve execution without understanding that the skill can access external services and potentially sensitive credentials.
