content-research-writer
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from the user (writing drafts) and external web sources (research). This creates an attack surface where malicious instructions could be embedded in the text being analyzed or researched.
- Ingestion points: Processes user-provided article drafts and external information retrieved during the 'Conduct Research' phase (SKILL.md, Instructions 3 and 5).
- Boundary markers: The instructions lack explicit boundary markers or directives to treat embedded instructions in user drafts as data rather than commands.
- Capability inventory: The workflow involves reading from and writing to the local file system and performing web searches (SKILL.md, Setup Your Writing Environment).
- Sanitization: No specific sanitization or validation of external content or user-provided text is specified.
Audit Metadata