tailrocks-graphql-best-practices

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and evolve untrusted repository content, including SDL snapshots, source code, and tool outputs. This creates a surface for indirect prompt injection.
  • Ingestion points: Identified in references/runtime-trust.md as repository files, reports, fixtures, scripts, registry content, and web content.
  • Boundary markers: The skill includes a dedicated runtime-trust.md reference that explicitly instructs the agent to treat all repository data as untrusted and prevents it from altering scope or authority.
  • Capability inventory: The skill involves writing and modifying source code and schemas, and executing development tools like cargo and bun via subprocess calls.
  • Sanitization: The skill enforces contract integrity through mandatory schema snapshotting and breaking-change diffs using graphql-inspector as detailed in references/contract-gates.md.
  • [COMMAND_EXECUTION]: The instructions involve executing standard development and build tools, including cargo for Rust compilation/schema generation and bun for TypeScript codegen and contract gating. These commands are standard for the intended use case of evolving a GraphQL service and are scoped to the local project environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 03:12 PM
Security Audit — agent-trust-hub — tailrocks-graphql-best-practices