research-assistant

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFE
Full Analysis
  • Indirect Prompt Injection (SAFE): The skill is designed to process untrusted web data.
  • Ingestion points: WebSearch results (referenced in process and guidelines).
  • Boundary markers: No specific delimiters or boundary warnings are present in the instructions.
  • Capability inventory: The skill uses WebSearch to gather data for analysis and synthesis.
  • Sanitization: No explicit sanitization or filtering of external content is defined. This surface is considered safe as it is essential to the skill's primary purpose.
  • Prompt Injection (SAFE): No instructions were found that attempt to override agent behavior or bypass safety guidelines.
  • Data Exposure & Exfiltration (SAFE): No hardcoded credentials, sensitive file paths, or unauthorized network operations were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 04:13 AM