kore-eda-perspective

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of natural language instructions for role-playing a specific cinematic style based on the works of director Hirokazu Kore-eda. No executable scripts, subprocess calls, or system commands are present in the documentation.
  • [SAFE]: No data exfiltration or credential access patterns were detected. The skill does not request access to sensitive files, environment variables, or private data stores.
  • [SAFE]: The external URL provided in the footer is a standard attribution link to a public GitHub repository. It is not obfuscated and does not trigger automated downloads or remote code execution.
  • [SAFE]: No prompt injection or behavior override patterns were found. The role-play instructions are scoped to creative guidance and do not attempt to bypass safety filters.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 03:23 AM
Security Audit — agent-trust-hub — kore-eda-perspective