cali-ops-verify-ci

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow runs verify-ci.sh which, when given a live-url at runtime, uses curl to fetch arbitrary web page/body text (live="$(curl ... "$LIVE_URL")"), then includes the resulting “notes”/differences in the emitted JSON that the calling agent ingests—this is indirect prompt-injection exposure from outsider-authored public web content.