researchers-historical

Pass

Audited by Gen Agent Trust Hub on Feb 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): The skill possesses a surface area for indirect prompt injection (Category 8) due to its dependency on external web data.
  • Ingestion points: The skill utilizes WebFetch and WebSearch to ingest data from various third-party archives and news repositories.
  • Boundary markers: Absent. There are no explicit instructions or delimiters used to prevent the agent from following instructions potentially embedded in the historical documents or archived web pages it retrieves.
  • Capability inventory: The skill is granted Write, Edit, WebFetch, and WebSearch tools, allowing it to modify local files based on external input.
  • Sanitization: Absent. The skill extracts facts and contemporary quotes directly from retrieved content without a validation or sanitization layer.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 22, 2026, 06:38 AM