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

ai-content-pipeline

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the belt CLI tool via the Bash tool to automate media generation tasks. This aligns with the skill's intended purpose as an automation pipeline for the inference.sh platform.
  • [EXTERNAL_DOWNLOADS]: Provides a link to installation instructions on the official inference-sh GitHub repository. This is a reference to documentation and does not involve the automatic execution of remote scripts or packages.
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface in the 'Blog to Video Pipeline' where user-provided content is processed into scripts and images.
  • Ingestion points: Data enters the workflow from <blog-content> in the 'Blog to Video Pipeline' section of SKILL.md.
  • Boundary markers: None identified for the data interpolated into shell commands.
  • Capability inventory: The skill uses the Bash tool to execute belt CLI commands across all pipeline stages (text, image, video, audio).
  • Sanitization: No explicit sanitization or validation of processed external content is implemented before use in command arguments.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 02:28 AM
Security Audit — agent-trust-hub — ai-content-pipeline