bc-widgets

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md "Before writing code" section explicitly instructs the agent to "Fetch https://developer.bigcommerce.com/docs/storefront/widgets" and to perform web searches (e.g., "Web-search bigcommerce page builder widgets custom"), which requires loading open/public third‑party web content that the agent will read and use to guide implementation decisions—exposing it to untrusted external content that could influence actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent to "Fetch https://developer.bigcommerce.com/docs/storefront/widgets" at runtime to obtain live documentation that would directly guide implementation/prompting, so this external URL can control agent instructions.