review-ui

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs legitimate code review and quality assurance tasks within the local project environment using established git tools and internal documentation.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests and processes untrusted source code and documentation from the repository.
  • Ingestion points: Source code files, markdown documentation, and git diff output are read into context.
  • Boundary markers: Absent; file content is analyzed without specific delimiters to ignore embedded instructions.
  • Capability inventory: File system access (reading docs/code), shell execution (git, python), and sub-agent spawning via the spawn_agent tool.
  • Sanitization: The skill implements an 'Evidence-Based Reasoning' protocol and a 'Why-Review' self-validation gate that requires 'file:line' citations for all findings, effectively mitigating the risk of following malicious instructions embedded in the analyzed data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 09:55 PM
Security Audit — agent-trust-hub — review-ui