code-design-review

Pass

Audited by Gen Agent Trust Hub on Oct 4, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill consists entirely of markdown instructions and informational references. It does not include any scripts, executable binaries, or commands to install external packages.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to analyze user-provided code and design documents, which constitutes an attack surface for indirect prompt injection. Malicious instructions could potentially be embedded in comments or metadata within the subject files. This risk is minimized by the skill's explicit constraints, which limit the agent to generating a report and strictly prohibit file modifications, commits, or shell execution (e.g., "Report only; no edits", "No edits, commits, or pushes").
  • [EXTERNAL_DOWNLOADS]: The skill references several external informational URLs for engineering principles (e.g., Stanford University, GitHub, Stack Overflow, and various engineering blogs). These are used for documentation and theoretical context rather than as sources for executable code or automated downloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 4, 2026, 04:42 AM