Description-Behavior Mismatch
- Category
- MCP Tool Poisoning
- Confidence
- 98% confidence
- Finding
The supplied script's primary function is linting, not building the interview kit promised by the description. It does not create role-specific questions, follow-up probes, competencies, or scoring criteria; it merely checks whether corresponding section labels occur in supplied text. Its banned-phrase checks partially support the declared flagging function but are narrow and context-insensitive, including flagging phrases quoted in a do-not-ask list. File reads and report writes are ordinary supporting implementation details; no unrelated resource access or hidden capabilities are evident.
- Content
