04-script-video-global
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill features an indirect prompt injection surface by ingesting data from external sources to inform its output.
- Ingestion points: It reads product and marketing context from files in the
.agents/directory and processes user-provided reference video links. - Boundary markers: The instructions do not specify boundary markers or instructions to disregard embedded commands within the ingested data.
- Capability inventory: The skill's functionality is limited to generating text-based scripts, captions, and scores; it does not utilize network tools, file-writing capabilities, or shell execution.
- Sanitization: There is no evidence of sanitization or validation for the content retrieved from the context files or external links.
Audit Metadata