graphql-dev
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it fetches and processes external data from documentation websites.
- Ingestion points: External content is fetched from docs.saleor.io, the-guild.dev, and graphql.org using WebSearch and WebFetch.
- Boundary markers: The instructions lack specific delimiters or instructions to ignore potential commands embedded in the fetched documentation.
- Capability inventory: The skill is configured with Bash, Write, and Edit tools, which represent a significant capability tier if an injection were successful.
- Sanitization: No validation or sanitization of the fetched external data is required by the instructions.
- [EXTERNAL_DOWNLOADS]: The skill references documentation and configuration from well-known and reputable services including Saleor, GraphQL.org, and The Guild. These references are standard for the stated development purpose.
Audit Metadata