research

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions.
  • Ingestion points: External documentation, source code, and API references mentioned in SKILL.md.
  • Boundary markers: Instructions lack explicit delimiters to separate external data from agent commands.
  • Capability inventory: The agent has permissions to write research results to the repository.
  • Sanitization: Content from external sources is not sanitized or escaped before being written to files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 03:54 PM
Security Audit — agent-trust-hub — research