ai-content-pipeline
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute the infsh CLI for orchestrating media pipelines. It includes logic for executing shell loops to process multiple content items dynamically.- [EXTERNAL_DOWNLOADS]: The skill interacts with APIs and models from well-known services including Google, ByteDance, OpenRouter, and Fal.ai. It also utilizes resources from the vendor's own platform at inference.sh.- [PROMPT_INJECTION]: An indirect prompt injection surface is present because the skill interpolates untrusted data, such as blog content or script text, directly into shell command strings.
- Ingestion points: Untrusted script and blog content referenced in SKILL.md.
- Boundary markers: None present in the provided shell templates to delimit user input.
- Capability inventory: The Bash tool is used to execute all CLI-based pipeline steps.
- Sanitization: There is no evidence of input escaping or validation within the provided workflow examples.
Audit Metadata