constructive-graphql-codegen

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes npx to execute the @constructive-io/graphql-codegen tool for generating React Query hooks, ORM clients, and CLI interfaces from GraphQL sources.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @constructive-io/graphql-codegen package from the npm registry, which is a resource owned and maintained by the skill author.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface through its generation of AGENTS.md and the skills/ directory from external GraphQL schemas.
  • Ingestion points: Schema data is retrieved from GraphQL endpoints, local schema files, and live PostgreSQL databases.
  • Boundary markers: No specific delimiters or instructions to ignore embedded instructions are identified in the generated documentation output intended for agent consumption.
  • Capability inventory: The skill includes the ability to write generated code and documentation to the local filesystem and provides a framework for executing generated CLI commands.
  • Sanitization: There is no evidence of sanitization of GraphQL metadata, such as field or type descriptions, before it is used to generate documentation for AI agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 08:20 AM