skills/brightdata/skills/rag-pipeline/Gen Agent Trust Hub

rag-pipeline

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to process arbitrary web content retrieved via the discover tool and feed it directly into LLM prompts, creating a surface for indirect prompt injection.
  • Ingestion points: Page content is retrieved from the discover API and processed in SKILL.md and references/code.md.
  • Boundary markers: Content is separated using simple text headers and numerical indices, lacking robust escaping for adversarial content.
  • Capability inventory: The skill code interacts with the discover API (network access), vector databases (data persistence), and LLM APIs.
  • Sanitization: Implementation includes logic to filter out common block pages based on regex patterns and length, but does not sanitize content for adversarial LLM instructions.
  • [EXTERNAL_DOWNLOADS]: The skill references several standard and vendor-maintained libraries for its implementation.
  • Node.js packages: Uses @brightdata/sdk, openai, and pg.
  • Python packages: Uses brightdata.
  • Remote references: The skill demonstrates interactions with the official Bright Data and OpenAI APIs.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 05:55 AM
Security Audit — agent-trust-hub — rag-pipeline