content-research-writer
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is designed to assist users with writing blog posts, articles, and technical documentation. It provides structured templates for outlining, feedback, and citation management, which are consistent with its stated purpose.\n- [INDIRECT_PROMPT_INJECTION]: The skill presents an inherent surface for indirect prompt injection as it processes external research and user-provided drafts.\n
- Ingestion points: Research data from external sources and user-provided draft sections (e.g., hooks, introductions) processed during the writing workflow in SKILL.md.\n
- Boundary markers: None identified in the prompt instructions to delimit untrusted data.\n
- Capability inventory: The skill guides the agent to perform web searches for research and interact with the local file system (e.g., article-draft.md) for writing tasks.\n
- Sanitization: No specific sanitization or filtering of external content is defined in the instructions.
Audit Metadata