zhou-xingchi-director
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a creative writing and directing tool based on public knowledge of Stephen Chow's filmography and methods. It explicitly instructs the agent not to impersonate the individual or claim private knowledge.
- [DATA_EXPOSURE_AND_EXFILTRATION]: No sensitive data access or network exfiltration patterns were found. The skill references legitimate news and media domains (China Daily, China News, Sina, CCTV, People's Daily) for source material, which is consistent with its stated purpose.
- [REMOTE_CODE_EXECUTION]: There are no patterns involving remote script downloads, package installations, or dynamic code execution.
- [OBFUSCATION]: No obfuscated text, base64-encoded commands, or hidden characters were detected in any of the skill files.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided story ideas but maintains strict boundaries using internal reference files and explicit instructions to prevent behavior override.
Audit Metadata