deep-research

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill defines a research workflow that requires the agent to ingest external data (search results, documentation, source code), which creates a surface for indirect prompt injection.
  • Ingestion points: External research sources and primary materials retrieved during the research process (SKILL.md).
  • Boundary markers: The skill does not provide specific instructions for using delimiters or boundary markers when processing these external inputs.
  • Capability inventory: The skill implies the use of search and retrieval tools to access external content.
  • Sanitization: The instructions focus on weighing source quality but do not include technical sanitization or validation of the ingested data content.
  • [NO_CODE]: The skill is composed entirely of markdown instructions and does not contain any scripts, binary files, or external package dependencies.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 03:40 PM
Security Audit — agent-trust-hub — deep-research