ta-findings-writer
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is purely instructional and intended for academic writing. It does not involve sensitive file access, network requests, or command execution.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data including theme summaries and interview quotes provided by the user or upstream analysis tools (SKILL.md). While there are no explicit boundary markers or sanitization logic to handle instructions potentially embedded in quotes, the risk is low as the skill's capabilities are limited to generating a markdown document via the Write tool.
Audit Metadata