deep-research

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external data during its research phase, which introduces a vulnerability surface for indirect prompt injection.\n
  • Ingestion points: External information is gathered and synthesized by scripts/research.py from search results and web content.\n
  • Boundary markers: The skill documentation does not specify the use of delimiters or specific instructions to prevent the agent from following commands embedded in external research data.\n
  • Capability inventory: The skill executes local logic via scripts/research.py to perform multi-step research tasks and interact with external APIs.\n
  • Sanitization: There is no documentation of content sanitization or validation for the data retrieved from external sources before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 02:14 AM
Security Audit — agent-trust-hub — deep-research