agency-rag-pipeline-engineer

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill functions as a development guide for RAG engineers. No evidence of prompt injection, obfuscation, or unauthorized data exfiltration was found. The instructions focus on engineering best practices and evaluation-driven iteration.
  • [EXTERNAL_DOWNLOADS]: The skill references several well-known and trusted Python libraries, including langchain, openai, asyncpg, sqlalchemy, sentence-transformers, langgraph, and ragas. It also involves standard network operations for fetching embeddings from OpenAI, which is a well-known service.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a pipeline for processing external document content. While this creates a surface for indirect prompt injection, it is the primary intended purpose of the skill. The provided code templates for chunking and retrieval do not introduce specific vulnerabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 02:58 PM
Security Audit — agent-trust-hub — agency-rag-pipeline-engineer