react-doctor

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

• Third-party content exposure detected (low risk: 0.10). The workflow fetches external playbook and rule markdown prompts via HTTP from www.react.doctor, which are then ingested by the agent as instructions and context during the /doctor triage workflow.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill fetches behavior-selecting prompt instructions and rules from react.doctor (an arbitrary third-party domain) at runtime, introducing an operational dependency with weak/unknown provenance.