workflow-init

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly instructs the agent to "Fetch and follow the getting-started guide" from public URLs such as https://useworkflow.dev/docs/getting-started/next, meaning it will ingest and act on external, third‑party web content that can influence tool use and next actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly fetches and follows at runtime the external getting-started guides hosted on https://useworkflow.dev/docs/getting-started/ (e.g., https://useworkflow.dev/docs/getting-started/next), so remote content would directly control the agent's installation instructions and execution flow.