jk-jenkins-cli

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

• Third-party content exposure detected (high risk: 0.72). The required runtime workflow for this skill is to run jk against user-supplied Jenkins URLs and then ingest Jenkins pipeline/build/log text (e.g., stage logs and pendingInput) into the agent context; Jenkins content is outsider-authored (other users/teams’ pipeline logs and input text), creating an indirect prompt-injection path via jk build logs / jk build status -o json outputs.