cocos-creator

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides legitimate development assistance for Cocos Creator projects. It includes a diagnostic script (scripts/cocos_doctor.py) that performs static analysis on project files for missing metadata and legacy API usage without performing any dangerous system calls or network operations.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze project files (scripts, configurations, and metadata) which is a standard surface for indirect prompt injection.
  • Ingestion points: Reads project.json, package.json, and .ts source files via Bash commands and scripts/cocos_doctor.py.
  • Boundary markers: None explicitly defined.
  • Capability inventory: Uses Bash to execute local diagnostic tools and project searches.
  • Sanitization: Performs regex-based static analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 04:21 PM