deep-research

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a legitimate research workflow using built-in tools for their intended purpose. It does not contain hardcoded credentials, obfuscated logic, or unauthorized system commands.
  • [PROMPT_INJECTION]: Indirect Prompt Injection Risk Assessment:
  • Ingestion points: Untrusted content is fetched from the web via the WebFetch tool.
  • Boundary markers: There are no explicit delimiters defined in the instructions to separate fetched content from system instructions.
  • Capability inventory: The skill has access to WebSearch and WebFetch tools.
  • Sanitization: No specific filtering or sanitization steps are defined for processing external web data.
  • Note: While this establishes a standard attack surface for web-based research skills, there is no evidence of malicious intent or instructions within the skill itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 03:53 AM