prompt-videos
Pass
Audited by Gen Agent Trust Hub on May 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains only instructional content and prompting strategies. No scripts, shell commands, or automation logic are present, precluding technical attack vectors like remote code execution or privilege escalation.
- [EXTERNAL_DOWNLOADS]: Includes several links to the official Replicate blog for further learning. These resources are from a trusted source and align with the skill's stated purpose.
- [PROMPT_INJECTION]: While the skill provides instructions on how to phrase prompts (e.g., "No subtitles!"), these are intended for the target video generation models and do not attempt to override the AI agent's own safety constraints or system instructions.
Audit Metadata