Skills
Navigate
skills/inference-sh/skills/ai-content-pipeline/Gen Agent Trust Hub

ai-content-pipeline

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill acts as a comprehensive guide and template for using the inference.sh CLI to build media automation workflows.
  • [EXTERNAL_DOWNLOADS]: The skill references core dependencies from the official belt-sh and inference-sh organizations on GitHub and NPM.
  • Evidence: Installation instructions for belt-sh/cli and inference-sh/skills repositories.
  • [PROMPT_INJECTION]: The skill demonstrates processing external content through multiple pipeline stages, creating a surface for indirect prompt injection.
  • Ingestion points: Workflows in SKILL.md interpolate variables like <blog-content> and <script-text> into model prompts.
  • Boundary markers: The examples do not include explicit delimiters or safety instructions to isolate external content.
  • Capability inventory: The skill utilizes the Bash tool to run belt app run commands and perform file operations.
  • Sanitization: No input sanitization or validation logic is provided in the examples.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 06:32 PM
Security Audit — agent-trust-hub — ai-content-pipeline