researchers-journalism
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the web using
WebSearchandWebFetchtools to gather journalistic sources. - Ingestion points: External websites, news articles, and investigation reports retrieved during the research process as defined in
SKILL.mdandSOURCE_EXTRACTION.md. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded in the retrieved web content.
- Capability inventory: The skill has access to
WebSearch,WebFetch,Write, andEdittools, which allow it to both read from the open web and modify the local filesystem. - Sanitization: There is no explicit logic for sanitizing or filtering the content fetched from external sources before it is processed and summarized by the agent.
Audit Metadata