create-video-implementation-workflow
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it ingests untrusted external data to generate instructions and shell commands for other agents.
- Ingestion points: Approved concept brief and script inputs defined in
SKILL.md. - Boundary markers: The instructions do not define explicit delimiters or instructions to ignore embedded commands within the input brief/script.
- Capability inventory: The skill generates a
workflow.mdfile containing shell commands (e.g.,ffprobe,ffmpeg) and pseudocode meant for execution by a coding agent. - Sanitization: No explicit sanitization or validation logic is defined for the external input before it is incorporated into the generated workflow output.
Audit Metadata