people-research

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted web content, creating a potential surface for indirect prompt injection.\n
  • Ingestion points: Search results retrieved from the web via the web_search_advanced_exa tool as described in SKILL.md.\n
  • Boundary markers: The skill instructs the agent to maintain 'Token Isolation' by using separate Task agents for processing results.\n
  • Capability inventory: The skill utilizes advanced web search and data distillation capabilities.\n
  • Sanitization: Employs a sub-agent architecture to distill and summarize search data before it is returned to the main context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 06:52 AM