rag-architect

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of instructional documentation and architectural advice for building RAG systems. No executable code, shell scripts, or malicious prompt instructions were found.
  • [PROMPT_INJECTION]: The provided prompt template for RAG includes explicit boundary instructions ("Answer the question based ONLY on the following context") which is a standard best practice to prevent the model from ignoring the provided data.
  • [EXTERNAL_DOWNLOADS]: The skill references documentation from LangChain and educational videos on YouTube, both of which are well-known and trusted platforms.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 07:17 PM