skills/inf-sh/skills/ai-rag-pipeline/Gen Agent Trust Hub

ai-rag-pipeline

Fail

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill provides an installation command that pipes a remote script directly to a shell (curl -fsSL https://cli.inference.sh | sh). This script is hosted on the vendor's own domain.
  • [EXTERNAL_DOWNLOADS]: The skill downloads installation scripts and binaries from cli.inference.sh and dist.inference.sh as part of its setup instructions.
  • [COMMAND_EXECUTION]: The skill utilizes the infsh CLI tool via Bash to perform search, extraction, and LLM processing. The execution is restricted to the infsh command prefix in the skill configuration.
  • [PROMPT_INJECTION]: The skill documentation exhibits an indirect prompt injection surface:
  • Ingestion points: External content from web searches and URL extraction (Tavily/Exa) is stored in shell variables (e.g., $SEARCH_RESULT, $CONTENT) in SKILL.md.
  • Boundary markers: Absent; external content is directly interpolated into prompt strings without delimiters or instructions to ignore embedded commands.
  • Capability inventory: The infsh tool can interact with various LLMs (Claude, GPT-4, Gemini) and search engines through the Bash tool in SKILL.md.
  • Sanitization: Absent; there is no logic provided to escape or validate the retrieved web content before it is passed to the LLM apps.
Recommendations
  • HIGH: Downloads and executes remote code from: https://cli.inference.sh - DO NOT USE without thorough review
Audit Metadata
Risk Level
HIGH
Analyzed
Apr 4, 2026, 09:10 PM
Security Audit — agent-trust-hub — ai-rag-pipeline