go-in-depth
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external websites, creating a surface for indirect prompt injection attacks.
- Ingestion points: In
scripts/workflow-script.js, theFETCH_PROMPTinstructs an agent to useWebFetchto retrieve content from URLs discovered viaWebSearch. - Boundary markers: The
FETCH_PROMPTlacks robust boundary markers (e.g., XML tags or clear delimiters) to separate the system instructions from the fetched external content. It does not explicitly instruct the agent to ignore any instructions contained within the fetched text. - Capability inventory: The skill has the capability to perform further
WebSearchqueries,WebFetchoperations, and multiple LLM agent calls. While it does not appear to have file-write or shell execution capabilities, an injection could influence the direction of the research or the final report's content. - Sanitization: There is no evidence of sanitization, filtering, or escaping of the content retrieved via
WebFetchbefore it is passed to the extraction agent.
Audit Metadata