ai-rag-pipeline

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill implements a Retrieval Augmented Generation (RAG) architecture, which involves processing untrusted data from external web sources.
  • Ingestion points: The skill uses tools like tavily/search-assistant, exa/search, and tavily/extract to fetch live data from the internet as described in SKILL.md.
  • Boundary markers: The provided examples interpolate search results directly into LLM prompts using shell variables (e.g., $SEARCH_RESULT) without explicit delimiters or instructions to ignore embedded commands.
  • Capability inventory: The skill utilizes the Bash(belt *) tool to perform network operations and interact with external AI and search APIs.
  • Sanitization: No explicit sanitization or filtering of the retrieved web content is shown in the research templates.
  • [EXTERNAL_DOWNLOADS]: The skill references external installation instructions and components within the platform ecosystem.
  • References: The skill recommends adding the belt-sh/cli component for platform access.
  • Resource Links: Provides links to installation guides and documentation hosted on inference.sh and associated GitHub repositories.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 05:03 AM
Security Audit — agent-trust-hub — ai-rag-pipeline