journey-builder

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

• Third-party content exposure detected (high risk: 1.00). The skill's Step 0 explicitly requires fetching and reading all files from a public GitHub Gist (gh gist view 84a5c108d5742c850704a5088a3f4cbf) and instructs the agent to "Apply every relevant pitfall to your work in this session," meaning untrusted, user-authored content is ingested and can directly influence actions and decisions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's mandatory Step 0 instructs the agent at runtime to fetch and apply content from the shared pitfalls gist via "gh gist view 84a5c108d5742c850704a5088a3f4cbf" (https://gist.github.com/84a5c108d5742c850704a5088a3f4cbf), and that fetched content is required and directly steers the agent's behavior, so it is a runtime external dependency that can control prompts.