ai-content-pipeline
Pass
Audited by Gen Agent Trust Hub on May 7, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches installation instructions and complementary skill modules from the vendor's official GitHub organization (inference-sh).
- [COMMAND_EXECUTION]: Utilizes the
beltCLI andnpxto orchestrate multi-step workflows. These commands are integral to the skill's purpose and are performed within the scope of the platform's content pipeline environment. - [PROMPT_INJECTION]: The skill is designed to process and chain data between various AI models (e.g., generating a script then converting it to audio). While this involves processing untrusted model outputs, it is the intended primary function of the content pipeline and lacks malicious patterns.
- Ingestion points: Output from Claude, Kokoro TTS, and FLUX models interpolated into subsequent tool calls in
SKILL.md. - Boundary markers: Absent in command templates.
- Capability inventory: Orchestration of remote AI apps via the
beltCLI tool. - Sanitization: Not explicitly implemented in the provided workflow templates.
Audit Metadata