deep-research
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown content with no executable scripts, configuration files, or external dependencies.
- [INDIRECT_PROMPT_INJECTION]: Ingestion points: The skill processes untrusted data from external sources during the research phase. Boundary markers: The instructions mandate the use of direct quotes and citations to delimit external content. Capability inventory: The skill contains no executable scripts, subprocess calls, or automated tools. Sanitization: It requires rigorous verification of claims against primary sources and the explicit separation of fact from inference.
Audit Metadata