research

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill establishes a structured process for sub-agents to perform research using official documentation and source code. It emphasizes data integrity by requiring citations and limiting sources to first-hand materials.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external data (web documentation, public source code), which creates a theoretical attack surface for indirect prompt injection. However, the skill's capabilities are limited to repository file-writing in Markdown format, which does not present a high security risk.
  • Ingestion points: External documentation, source code, and API specifications retrieved by sub-agents.
  • Boundary markers: None explicitly defined in the provided instructions.
  • Capability inventory: Writing Markdown files to the local repository.
  • Sanitization: No explicit sanitization or filtering of the ingested content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 02:16 AM
Security Audit — agent-trust-hub — research