constructive-architecture

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The architecture defines an ingestion surface where the agent processes external configuration files like app-brief.yaml and TypeScript Blueprints to drive platform provisioning.\n
  • Ingestion points: app-brief.yaml and TypeScript BlueprintDefinition objects defined in the scripts.\n
  • Boundary markers: Not explicitly defined within the provided documentation.\n
  • Capability inventory: The skill triggers platform actions via GraphQL API calls and local shell script execution using pnpm.\n
  • Sanitization: The documentation does not specify sanitization or validation protocols for the provided blueprint inputs.\n- [DYNAMIC_EXECUTION]: The provisioning workflow involves running local TypeScript scripts (pnpm run provision) that interpret and execute logic defined in blueprints. This dynamic behavior is a core component of the platform's automated setup process.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 01:06 PM
Security Audit — agent-trust-hub — constructive-architecture