content-research-writer
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources and user-provided samples, creating a potential path for indirect prompt injection.
- Ingestion points: Instructions in
SKILL.md(Step 3 and Step 6) describe searching for relevant information from external sources and reading existing writing samples to learn the user's style. - Boundary markers: The instructions do not specify the use of delimiters (like XML tags or triple quotes) or explicit warnings for the agent to ignore instructions embedded in the external content.
- Capability inventory: The skill is designed to perform file operations, including creating and updating
outline.md,research.md, and various draft versions. - Sanitization: There are no instructions provided to sanitize, filter, or validate the content fetched from external research sources before it is processed or incorporated into documents.
Audit Metadata