laravel-review

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses dynamic context injection (the ! syntax) to execute local git diff commands. These commands are necessary to provide the agent with the code changes it is tasked to review. They are read-only and restricted to the repository context.
  • [PROMPT_INJECTION]: The skill processes untrusted code content, which presents a surface for indirect prompt injection. Ingestion points: Untrusted data enters via git diff outputs in SKILL.md. Boundary markers: Content is wrapped in code blocks, but no specific 'ignore instructions' warnings are used. Capability inventory: The skill uses git and file reading tools (Read, Grep, Glob) as defined in the frontmatter. Sanitization: There is no automated sanitization of the code being reviewed. This risk is inherent to the tool's purpose and mitigated by the detailed audit checklist provided to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 11:24 AM