graphql
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use CLI tools for schema verification and linting. Specifically, it guides the use of
npx @graphql-eslint/eslint-pluginfor static analysis of documents andnpx @graphql-inspector/cli difffor breaking change detection. These are standard developer tools used within their intended purpose. - [EXTERNAL_DOWNLOADS]: The workflows suggest using tools from the NPM registry via
npx. The referenced packages are well-known community standards for GraphQL development. The skill also references documentation and repositories from trusted organizations including the GraphQL Foundation, Apollo GraphQL, and the Guild (GraphQL Yoga). - [INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting and analyzing user-provided GraphQL schemas and operation documents. While this presents a surface for processing untrusted content, the skill uses these inputs for structural analysis (linting, diffing) rather than direct execution of embedded instructions. The severity is low as it relies on standard parsing libraries.
Audit Metadata