content-research-writer
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external research data and user-provided drafts, creating an attack surface for indirect instructions hidden within that data. \n- Ingestion points: The skill ingests data through user-provided article drafts and external research content as defined in the Instructions and Examples sections of SKILL.md. \n- Boundary markers: The instructions and provided templates do not utilize specific delimiters or instructions to ignore embedded commands within the processed text. \n- Capability inventory: The skill utilizes local file reading and writing capabilities to manage outlines, research files, and drafts within the designated project folder. \n- Sanitization: There is no evidence of specific sanitization, filtering, or escaping of the ingested content before it is processed by the agent.
Audit Metadata