ai-rag-pipeline

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill demonstrates patterns for ingesting untrusted data from external sources (web searches via Tavily/Exa and URL extraction) and interpolating that data directly into LLM prompts. This creates a surface for indirect prompt injection. If an attacker-controlled website appears in search results, its content could potentially override the agent's instructions during the generation phase.
  • Ingestion points: Data is retrieved into variables like $SEARCH_RESULT, $TAVILY, $EXA, and $CONTENT via CLI tool outputs.
  • Boundary markers: The examples use descriptive headers (e.g., 'Search Results:', 'Source 1 (Tavily):') to separate context from the main prompt, which provides minimal structure but does not include explicit safety instructions to ignore embedded commands.
  • Capability inventory: The skill uses the belt CLI (allowed via allowed-tools) to execute various remote applications, including LLMs and search engines.
  • Sanitization: The provided templates do not demonstrate any sanitization, filtering, or validation of the retrieved external content before prompt interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 06:03 PM
Security Audit — agent-trust-hub — ai-rag-pipeline