beforemerge-fullstack-architecture-review
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of Markdown-based documentation, rule sets, and code examples (Correct vs. Incorrect patterns). No executable scripts, obfuscated content, or unauthorized network operations are present.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external code provided by users during the review process (ingestion point). While it does not explicitly define boundary markers or sanitization logic for these inputs, it focuses on identifying security vulnerabilities in the reviewed code rather than executing instructions from it. This is a standard functional surface for code-review skills and does not represent a malicious intent.
- [SAFE]: All external references target reputable documentation sources (MDN, OWASP, React, Next.js, Martin Fowler) or the official vendor domains (beforemerge.dev, github.com/beforemerge). No suspicious external downloads or remote code execution patterns were found.
Audit Metadata