bounded-backend
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructional content and code examples for the Bounded platform. No malicious payloads or hidden functionalities were identified.
- [INDIRECT_PROMPT_INJECTION]: The skill documents interfaces that process external data, establishing a surface for indirect prompt injection. 1. Ingestion points: Function arguments (args), live game intents (intents), and agent inputs (input) as described in docs/functions.md, docs/live-runtime.md, and docs/agents-flue.md. 2. Boundary markers: The skill instructs developers to use auth rules and intentRules to gate access. 3. Capability inventory: Handlers have access to database writes (ctx.bounded), AI inference (ctx.ai), and network requests (ctx.fetch). 4. Sanitization: System integrity is maintained via declarative policy rules and invariants that validate state changes at the platform level.
Audit Metadata