content-research-writer
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill features an attack surface for indirect prompt injection by processing external research data and user writing samples.
- Ingestion points: External research findings and user-provided draft content (SKILL.md).
- Boundary markers: No explicit delimiters or instructions are provided to the agent to disregard instructions found within the research data.
- Capability inventory: The skill utilizes search tools and manages documents within the user's project directory.
- Sanitization: There are no instructions for sanitizing or escaping retrieved content before processing it.
- [NO_CODE]: The skill consists of instructional text and markdown templates without accompanying scripts or executable code.
Audit Metadata