skills/orziz/aiskills/review-anime/Gen Agent Trust Hub

review-anime

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a stylistic configuration designed for providing technical code reviews.- [COMMAND_EXECUTION]: The skill references standard file access and git diff operations necessary for code analysis. These operations are performed within the local repository context as intended.- [DATA_EXFILTRATION]: No network requests or data exfiltration mechanisms were detected. The skill operates strictly on the local codebase.- [PROMPT_INJECTION]: The instructions establish behavioral guidelines and persona constraints without attempting to bypass safety filters or extract system instructions. While the skill processes external code (an indirect injection surface), the rigid focus on technical review and specific dialogue formatting serves as a primary constraint.- [EXTERNAL_DOWNLOADS]: The skill does not involve downloading or executing any external code, scripts, or dependencies.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 08:14 AM