skills/89jobrien/langchainx/rag/Gen Agent Trust Hub

rag

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill acts as documentation for a RAG toolkit. It uses standard Rust patterns for trait definitions and provides safe code examples with placeholders for sensitive configuration like database connection strings.
  • [PROMPT_INJECTION]: The skill provides document loaders designed to ingest external data into an agent's context, creating a surface for indirect prompt injection.
  • Ingestion points: TextLoader, CsvLoader, HtmlLoader, PdfLoader, GitCommitLoader, HtmlToMarkdownLoader, and SourceCodeLoader (referenced in SKILL.md).
  • Boundary markers: The provided code snippets do not include explicit delimiter logic or instructions to ignore embedded commands.
  • Capability inventory: The skill uses ConversationalRetrieverChainBuilder and LLM invocations (e.g., OpenAI::default()) to process retrieved data (referenced in SKILL.md).
  • Sanitization: No explicit sanitization or escaping of external content is demonstrated in the examples.
  • Note: This represents the intended design of a RAG system and does not indicate malicious intent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 11:29 AM
Security Audit — agent-trust-hub — rag