neon-ai-gateway
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides patterns for building AI agents that ingest untrusted data from user prompts and tool outputs, creating a surface for indirect prompt injection.
- Ingestion points: User messages and tool execution results (e.g., the listTodos tool in SKILL.md) are fed into the LLM context.
- Boundary markers: The examples do not demonstrate the use of delimiters or specific instructions to ignore embedded commands in the processed data.
- Capability inventory: The skill enables database access via tools, tool execution loops, and network communication via the AI Gateway.
- Sanitization: No sanitization or validation of the ingested data is present in the provided code templates.
Audit Metadata