superplane-canvas-builder

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs using and requesting a raw token (e.g., superplane connect <URL> <TOKEN>) and tells the agent to ask the user to provide a URL and token, which encourages embedding secret values directly in commands/output.

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md workflow explicitly instructs the agent to fetch and inspect real provider payloads (e.g., "How to confirm payload fields" — run superplane executions list) and to use integration trigger data such as GitHub comment/body fields (see references/github.md showing root().data.comment.body) so the agent will ingest untrusted, user-generated webhook content that can directly influence expressions, branching, and subsequent tool actions.