spring-ai
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides code patterns that ingest user-controlled data into AI prompts, representing a standard indirect prompt injection surface for the documented technology.\n
- Ingestion points: Untrusted input is processed in
ChatService.java(chat,chatWithPrompt) andPromptService.java(generatePrompt).\n - Boundary markers: The examples do not demonstrate the use of delimiters or instructions for the AI to ignore embedded content.\n
- Capability inventory: The documented patterns enable network requests to large language model providers.\n
- Sanitization: As a functional guide, the snippets do not include input validation or sanitization logic.
Audit Metadata