content-research-writer
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process potentially untrusted content from external research sources and user-provided drafts to provide feedback, outlining, and citation services.
- Ingestion points: User-supplied sections for feedback and external content retrieved during the research process (SKILL.md, Instructions sections 3 and 5).
- Boundary markers: The instructions do not specify the use of delimiters or provide directives for the agent to ignore embedded commands within the analyzed text.
- Capability inventory: The skill involves file system interaction (creating and organizing writing projects) and implied web search functionality to gather research.
- Sanitization: There is no evidence of sanitization or validation routines for the external text processed by the agent.
Audit Metadata