code-reviewer

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze untrusted code, which is its primary function. This inherent surface is documented here as a neutral finding because the skill is strictly limited to read-only operations and has no capabilities to execute code, write files, or perform network exfiltration.
  • Ingestion points: Processes external code files and PR descriptions through the Read, Grep, and Glob tools.
  • Capability inventory: Restricted to read-only analysis tools and the generation of text reports.
  • Boundary markers: The workflow includes specific checkpoints and structured report sections to separate analysis from the data.
  • Sanitization: Relies on the host agent's internal safety mechanisms for processing code content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 05:57 PM
Security Audit — agent-trust-hub — code-reviewer