graphql-schema-generator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill's design permits the processing of untrusted user requirements and external network data through powerful tools without sufficient safety constraints.
  • Ingestion points: User-provided GraphQL requirements and potential responses from the curl tool.
  • Boundary markers: The skill metadata and instructions do not include delimiters or instructions to ignore embedded commands in the processed data.
  • Capability inventory: The skill is authorized to use Bash (curl), Write, Edit, and Grep, which provide a significant impact surface if the agent is manipulated.
  • Sanitization: No explicit sanitization, validation, or escaping logic for external inputs is defined within the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:30 PM