tech-route-comparison-zhcn
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources including technical papers, patent records, and web pages via tools like Exa, Tavily, and Jina.
- Ingestion points: External search results and page reading tools.
- Boundary markers: The instructions do not explicitly mandate strict delimiters (e.g., XML tags) for raw external content, though the workflow uses intermediate CSV files (
claim_ledger.csv,source_index.csv) which acts as a buffer. - Capability inventory: The skill is restricted to file operations and tool-based retrieval; it does not utilize
evalorexecfunctions. - Sanitization: There is no explicit requirement for escaping or filtering external content before interpolation.
- [EXTERNAL_DOWNLOADS]: The skill uses external search APIs and web readers (Exa, Tavily, Brave, Jina) to fetch technical evidence. These are standard tools for technical research and are used consistent with the primary purpose of the skill.
Audit Metadata