research

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data from external sources and write the output to the local repository.
  • Ingestion points: In SKILL.md, the agent is instructed to investigate primary sources such as official documentation, source code, specs, and first-party APIs.
  • Boundary markers: The instructions lack specific boundary markers or requirements to ignore instructions that might be embedded within the external sources being researched.
  • Capability inventory: The skill performs file system writes by saving findings as Markdown files in the repository (SKILL.md).
  • Sanitization: There are no requirements for sanitizing or validating the gathered content before it is committed to the repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 11:39 PM
Security Audit — agent-trust-hub — research