graphql-expert

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions include 'Iron Laws' and 'Anti-Patterns' that mandate critical security practices for GraphQL production environments, including query depth limiting and disabling schema introspection to prevent reconnaissance and Denial of Service (DoS) attacks.
  • [SAFE]: The provided JavaScript files (main.cjs, pre-execute.cjs, post-execute.cjs) contain only benign logic for help menus, metrics recording, and basic input validation. They do not perform any network operations or suspicious file system access.
  • [SAFE]: The 'Memory Protocol' section uses a standard local file read operation (cat .claude/context/memory/learnings.md) to maintain persistent state across agent sessions, which is an expected behavior in many agentic environments.
  • [SAFE]: No signs of prompt injection, data exfiltration, obfuscation, or unauthorized remote code execution were found during the analysis of the 10 files provided.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 02:04 PM