ai-rag-pipeline
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION] The skill implements a RAG (Retrieval Augmented Generation) pipeline that fetches content from external web search tools (Tavily, Exa) and interpolates the results directly into LLM prompts. This creates a surface for tool output poisoning where malicious instructions on web pages could influence the agent's behavior.
- [COMMAND_EXECUTION] The skill relies on the
Bash(belt *)tool to execute shell commands. It provides numerous examples of bash scripts that run thebeltCLI to interact with remote AI services. - [EXTERNAL_DOWNLOADS] The skill instructs the user to install external dependencies using
npx skills add belt-sh/cliand references other skills from theinference-shorganization.
Audit Metadata