ai-rag-pipeline
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: References installation instructions from the official inference-sh GitHub repository.
- [COMMAND_EXECUTION]: Demonstrates the use of the
beltCLI tool for search, extraction, and model inference via the Bash tool. - [PROMPT_INJECTION]: The skill defines a RAG architecture that interpolates external search data into prompts. Users should apply sanitization and boundary markers to mitigate indirect prompt injection from untrusted web content. \n
- Ingestion points: Interpolates results from Tavily and Exa searches into model prompts in SKILL.md. \n
- Boundary markers: Absent; data is placed directly into the prompt text. \n
- Capability inventory: Shell execution of the
beltCLI for data retrieval and model calls. \n - Sanitization: None; the examples use raw string interpolation.
Audit Metadata