gitnexus-debugging

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

• Third-party content exposure detected (medium risk: 0.30). The workflow ingests outsider free text through the user-provided query({query: "<error or symptom>"}) at runtime, which the agent uses to fetch/trace related execution flows in GitNexus.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's runtime workflow explicitly uses READ gitnexus://repo/{name}/process/{name} (e.g., gitnexus://repo/my-app/process/CheckoutFlow), indicating it fetches repository content at runtime that would be injected into the agent's context and used to control tracing/responses.