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