paw-mkt-psychology

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 explicitly instructs the agent to audit and fetch live public URLs and social sites (e.g., "Live Website URL Audit" in Shared Patterns / Pre-Flight and the agent-browser Research patterns for LinkedIn, Twitter/X, Facebook Ads Library with commands like agent-browser open/get text body), meaning it will ingest untrusted third-party web and social content that can influence recommendations and follow-up actions.