Tp4
- Category
- MCP Tool Poisoning
- Confidence
- 95% confidence
- Finding
The skill is described as a match predictor, but the documented behavior also includes reading a local secrets file, making authenticated outbound API requests, and reading/writing local cache data. This mismatch undermines informed consent and can hide sensitive operations behind a benign-seeming description, making misuse or over-privileged deployment more likely.
- Content
