Skills
skills/jeremylongshore/claude-code-plugins-plus-skills/langchain-sdk-patterns/Gen Agent Trust Hub

langchain-sdk-patterns

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill uses LangChain prompt templates that interpolate untrusted data (e.g., {text}), which represents a surface for indirect prompt injection if the processed content contains malicious instructions. \n- Ingestion points: The {text} placeholder within ChatPromptTemplate.from_template in SKILL.md. \n- Boundary markers: None present in the example code patterns. \n- Capability inventory: The skill is granted Read, Write, and Edit tool permissions. \n- Sanitization: No input validation or sanitization logic is provided in the SDK patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 06:23 PM