journey-loop

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

• Third-party content exposure detected (high risk: 1.00). This skill mandatorily fetches and incorporates full pitfall files from a public GitHub Gist (gh gist view 84a5c108d5742c850704a5088a3f4cbf) into the builder agent's prompt, exposing the agent to untrusted, user-generated third-party content that can materially influence its actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill mandatorily fetches and injects the contents of the GitHub Gist (gh gist view 84a5c108d5742c850704a5088a3f4cbf — https://gist.github.com/84a5c108d5742c850704a5088a3f4cbf) into the builder agent's prompt at runtime, so remote gist content directly controls agent instructions.