llm-app-patterns

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill documentation provides prompts and code snippets for RAG and Agent architectures that interpolate untrusted external data (e.g., retrieved document context, user queries) into LLM prompts.
  • Ingestion points: The RAG_PROMPT_TEMPLATE, REACT_PROMPT, and PromptTemplate class in SKILL.md accept external variables like {context}, {question}, and {text}.
  • Boundary markers: The prompts use simple text headers (e.g., 'Context:', 'Question:') which are weak delimiters against adversarial input attempting to escape the intended context.
  • Capability inventory: The patterns describe agents with tool-calling capabilities (ReActAgent, FunctionCallingAgent) and access to external vector databases.
  • Sanitization: The code examples do not include input sanitization, filtering, or escaping logic for the interpolated data, relying on the user to implement these safeguards.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 11:36 PM
Security Audit — agent-trust-hub — llm-app-patterns