content-research-writer
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and iterate upon user-provided content, creating an inherent surface for indirect prompt injection.
- Ingestion points: Data enters the agent context through user-supplied topics, introduction hooks, section drafts, and full article texts provided for review.
- Boundary markers: The instructions lack explicit delimiters or instructions to treat user-provided text as data only, which could allow instructions embedded in a draft to influence agent behavior.
- Capability inventory: The skill facilitates text analysis, research synthesis, and creative writing. It does not define any capabilities for sensitive file access, automated network operations, or privileged command execution.
- Sanitization: No mechanisms for filtering or sanitizing instructions within the ingested text are specified in the skill instructions.
Audit Metadata