04-script-video-global
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a structural prompt for the AI agent. It defines templates, hook formulas, and evaluation criteria for video scripts without introducing security risks.
- [DATA_EXPOSURE]: The skill instructs the agent to read context files from the
.agents/directory (e.g.,product-marketing-context-global.md). This is a standard pattern for providing project-specific context to the agent and does not involve exfiltration of sensitive system credentials or transmission of data to external servers. - [PROMPT_INJECTION]: No malicious prompt injection patterns, safety bypasses, or instructions to ignore previous rules were detected. The instructions focus entirely on the primary task of content generation.
- [REMOTE_CODE_EXECUTION]: There are no patterns involving remote code execution, package installations, or dynamic code generation. The skill does not use shell commands or external scripts.
Audit Metadata