reputation-management

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow and reference docs (SKILL.md, sentiment-monitoring.md, review-management-platforms.md) explicitly instruct ingesting and acting on untrusted public content — e.g., social media, review platforms like Google/Yelp/G2/Trustpilot, news/press and forums — which the agent is expected to read and which materially influence escalation, crisis tiering, and actions, creating a clear vector for indirect prompt injection.