NYC

frontend-code-review

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION] (LOW): The skill identifies a surface for indirect prompt injection by processing untrusted frontend code files (.tsx, .ts, .js).
  • Ingestion points: Untrusted source code files from pending changes or specific file paths.
  • Boundary markers: No explicit markers or instructions to ignore embedded prompts within comments are provided.
  • Capability inventory: The skill is designed to suggest and apply code fixes, implying write access to the filesystem.
  • Sanitization: No sanitization of the input source code is defined.
  • [NO_CODE] (SAFE): The skill consists entirely of markdown instructions (SKILL.md) and does not include any executable scripts, binaries, or external dependencies.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:32 PM