laohan-fenjingtishici

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill uses instructional templates to guide the AI in generating cinematography prompts. No patterns suggesting safety bypasses, instruction overrides, or jailbreak attempts were found.
  • [DATA_EXFILTRATION]: There are no network requests, credential access, or sensitive file reads. The skill only processes user-provided product descriptions and text strings.
  • [COMMAND_EXECUTION]: The skill performs local file system operations to save generated prompts as text files. These operations are limited to writing user-derived text to non-executable .txt files in a directory controlled by the user, which is appropriate for the skill's functionality.
  • [REMOTE_CODE_EXECUTION]: No remote scripts are downloaded or executed. The skill does not define or use any external package dependencies.
  • [OBFUSCATION]: All instructions and referenced templates are provided in plain text. No encoded content, hidden characters, or homoglyphs were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 11:03 PM
Security Audit — agent-trust-hub — laohan-fenjingtishici