langchain-text-splitters

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to install official @langchain libraries from the npm registry, which are recognized and well-known technology services.
  • [PROMPT_INJECTION]: The skill documents methods for ingesting content from external sources, which creates a potential surface for indirect prompt injection.
  • Ingestion points: The skill demonstrates loading data using PDFLoader and CheerioWebBaseLoader in SKILL.md.
  • Boundary markers: The provided code examples do not specify boundary markers or instructions to ignore embedded directions in the processed text.
  • Capability inventory: The code examples in SKILL.md utilize file system reading capabilities via PDFLoader and network request capabilities via CheerioWebBaseLoader.
  • Sanitization: The provided snippets do not include sanitization or validation of the content retrieved from external sources before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 04:36 PM
Security Audit — agent-trust-hub — langchain-text-splitters