workflow-ai-generation

Pass

Audited by Gen Agent Trust Hub on Jun 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides a configuration and guidance framework for using well-known technology libraries and open-source models (e.g., OpenAI Whisper, FLUX, CogVideoX, FFmpeg). No dangerous command execution, remote script downloads, or obfuscation techniques were detected.
  • [PROMPT_INJECTION]: As an orchestration skill for media synthesis, it exhibits an indirect prompt injection surface by passing user-supplied prompts through various AI generation pipelines. This is consistent with its primary purpose and lacks any intent to bypass safety guidelines.
  • Ingestion points: User input via the [prompt] argument and external media files (e.g., reference audio for voice cloning).
  • Boundary markers: Absent from the high-level workflow descriptions.
  • Capability inventory: Orchestrates external tools for audio/video synthesis, editing (FFmpeg), and cloud uploading (media-cloud-upload).
  • Sanitization: No explicit sanitization or input validation logic is present in the instructional markdown.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 27, 2026, 09:54 AM
Security Audit — agent-trust-hub — workflow-ai-generation