source-driven-development

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow (Step 2: “Fetch Official Documentation”) involves fetching documentation pages at runtime, which are external/public web content whose body text may be ingested into the agent’s LLM context, creating an indirect prompt-injection surface.

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 at runtime to fetch external documentation pages (e.g., https://react.dev/reference/react/useActionState#usage) and use their content to drive implementation and citations, meaning external pages directly control prompts/behavior.