real-time-backend
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to process user-supplied backend requirements to generate server-side implementation code, which is an attack surface for indirect prompt injection. This risk is managed by instructing the agent to implement strict input validation and schema-based verification. 1. Ingestion points: User-provided backend requirements. 2. Boundary markers: None. 3. Capability inventory: Code generation and architectural planning. 4. Sanitization: Explicitly mandates input validation at function boundaries and the use of schema validators.
- [EXTERNAL_DOWNLOADS]: The skill references documentation from a repository belonging to Convex, an established service provider, for additional context.
Audit Metadata