cross-verified-research

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements strong defensive rules to prevent hallucination and ensures high confidence in reported claims. It does not contain any instructions for unauthorized data access, persistence, or credential theft.
  • [PROMPT_INJECTION]: The skill's research pipeline involves ingesting external data, which creates an indirect prompt injection surface. Ingestion points: Untrusted data is retrieved from the web via WebSearch and WebFetch tools. Boundary markers: The instructions lack specific delimiters or instructions to ignore commands within the retrieved text. Capability inventory: The skill has access to powerful tools including Bash and WebFetch. Sanitization: There is no explicit content sanitization or validation logic described for the external data being processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 06:54 PM