nocodb

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes examples that embed credentials directly in commands (e.g., a DB connection string with user/password in the docker -e NC_DB value and curl examples with "xc-auth: YOUR_AUTH_TOKEN"), which encourages inserting real secrets verbatim into generated commands/outputs.

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

• Third-party content exposure detected (high risk: 0.70). The skill's instructions (SKILL.md) explicitly describe public Form Views ("Share via public URL") and Webhooks/Automations plus use of the auto-generated REST API with examples to list records (curl GET), which indicates the agent will read and act on untrusted, user-generated content submitted via public forms or webhooks; that third-party content could therefore influence subsequent actions.