ai-content-pipeline

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references installation instructions for the CLI tool hosted on the author's official GitHub repository (inference-sh/skills).
  • [COMMAND_EXECUTION]: The skill provides numerous examples for executing the 'belt' CLI tool to manage AI content workflows, as permitted by the frontmatter configuration.
  • [PROMPT_INJECTION]: The skill defines a multi-step content pipeline where data flows between AI tools (e.g., a script generated by an LLM is used as input for a TTS tool), creating an indirect prompt injection surface.
  • Ingestion points: Data from generated files (e.g., script.json, voice.json) is passed as input to subsequent 'belt app run' commands in SKILL.md.
  • Boundary markers: Absent; the examples do not use delimiters or instructions to ignore potential instructions embedded in the processed data.
  • Capability inventory: The skill utilizes the 'belt' CLI to execute various external AI models and perform media merging operations in SKILL.md.
  • Sanitization: Absent; the examples demonstrate direct interpolation of generated content into subsequent tool inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 01:11 PM