Tp4
High
- Category
- MCP Tool Poisoning
- Confidence
- 89% confidence
- Finding
- The documented purpose and security model do not fully match the described behavior: the skill supports additional device operations, token-cache management, and accepts credentials via command-line arguments despite emphasizing environment variables. This mismatch can mislead reviewers and users about what actions the skill can perform and expose secrets through shell history or process listings when CLI credentials are used.
