streaming-api-patterns
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides patterns for streaming LLM responses that ingest external data (e.g., user messages via
req.json()). This represents an attack surface for indirect prompt injection where malicious instructions could be embedded in the processed data. - Ingestion points:
SKILL.md(LLM Streaming Pattern section) andtemplates/sse-endpoint-template.ts. - Boundary markers: Not explicitly implemented in the simplified code examples.
- Capability inventory: Network communication via the OpenAI API and bidirectional data streaming.
- Sanitization: While not in the code snippets, the provided
checklists/streaming-checklist.mdexplicitly recommends sanitizing message content and validating origin headers as a security requirement.
Audit Metadata