hasura-graphql-engine

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt embeds literal secret-like values (DB passwords, HASURA_GRAPHQL_ADMIN_SECRET, JWT keys, API keys) directly in configuration and example commands, which encourages or requires the agent to output secrets verbatim in generated configs—creating an exfiltration risk.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly supports ingesting and executing data from external public services — e.g., Remote Schemas (add_remote_schema like https://countries.trevorblades.com/graphql or auth0 endpoints) and Event Triggers/Actions that call arbitrary webhooks (e.g., https://myapp.com/webhooks/...), so the agent will read and act on untrusted third‑party content.