Tp4
- Category
- MCP Tool Poisoning
- Confidence
- 99% confidence
- Finding
The skill is presented primarily as a conversational life-reflection assistant, but it also includes file-based report rendering and export behavior. That mismatch increases security risk because reviewers or runtime policy may underestimate the skill's actual capabilities, especially around reading Markdown inputs and writing HTML outputs that could expose sensitive personal data or be abused for unauthorized file generation.
- Content
