frontend-code-review

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION] (SAFE): Instructions are strictly focused on code review logic and do not contain attempts to override system safety or extract system prompts.
  • [DATA_EXFILTRATION] (SAFE): No network-enabled commands (curl, wget, fetch) or hardcoded credentials were found. The skill operates on local source files provided by the user.
  • [REMOTE_CODE_EXECUTION] (SAFE): The skill does not download or execute external scripts. It purely generates text-based review reports based on markdown templates.
  • [OBFUSCATION] (SAFE): No encoded strings, hidden characters, or homoglyphs were detected in the instructions or reference catalogs.
  • [INDIRECT_PROMPT_INJECTION] (LOW): While the skill ingests untrusted code for review, its capabilities are limited to generating a formatted report. It does not have dangerous tools (like shell access or file writing) that could be exploited via malicious comments in the code under review.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:36 PM