graphql-codegen

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE] (SAFE): No malicious patterns or security vulnerabilities detected across all 10 threat categories.
  • Prompt Injection: No attempts to override agent behavior or bypass safety filters were found in the skill or metadata.
  • Data Exposure & Exfiltration: No hardcoded credentials or access to sensitive local files (like SSH keys or AWS credentials) were detected. Network examples use local host addresses for debugging.
  • Unverifiable Dependencies: The skill recommends standard, well-known industry packages from the NPM registry (@graphql-codegen/cli, etc.).
  • Dynamic Execution: Python scripts included in the skill (validate.py) use yaml.safe_load() to prevent unsafe deserialization attacks.
  • Persistence & Privilege Escalation: No commands related to persistence (crontab, shell profiles) or privilege escalation (sudo, chmod 777) were found.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:08 PM