prototype-to-contract
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run the project's Relay compiler, type-checking, and build commands to synchronize generated GraphQL artifacts with the updated schema.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests prototype data, route entries, and local action hooks to generate production code. This data ingestion surface is a necessary part of the skill's primary function to refactor mock data into structured GraphQL queries.
- Ingestion points: Reads prototype data and mock hooks from the local repository (SKILL.md).
- Boundary markers: None explicitly defined for isolating embedded instructions in prototype files.
- Capability inventory: File system read/write for schema and components, and shell execution for Relay compiler and build tools.
- Sanitization: None specified for the content of the prototype files being processed.
Audit Metadata