content-research-writer
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and iterate on content provided by the user and data retrieved from external research sources.
- Ingestion points: It reads content from files like
article-draft.md,research.md, and potentially other local files within the dedicated project folder. It also ingests external data via search tools during the research phase. - Boundary markers: The instructions do not define specific delimiters or instructions to the agent to treat ingested writing samples or research text as untrusted data separate from its core instructions.
- Capability inventory: The skill has the ability to read and write files to the local file system and execute research/search tools to fetch external information.
- Sanitization: There is no evidence of sanitization, validation, or escaping logic applied to the external content before it is interpolated into the agent's reasoning process.
Audit Metadata