to-article
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external content to generate articles, creating a surface where malicious instructions embedded in source data could influence agent behavior.
- Ingestion points: The skill reads from
content/TOPIC.md,content/RESEARCH.md, and various external experiment reports to derive content. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between data and potential instructions within the source files.
- Capability inventory: The agent has the capability to read local project files and write the resulting draft to
content/ARTICLE.md. - Sanitization: The instructions do not specify any validation, filtering, or escaping of the content ingested from the research materials before processing.
Audit Metadata