meta-ads-intel

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

• Third-party content exposure detected (high risk: 0.90). The skill's onboarding (references/onboarding.md Phase 3a) explicitly instructs spawning a general-purpose subagent to scrape and analyze a user-supplied website URL using WebFetch/WebSearch, so the agent will fetch and interpret arbitrary public web content to populate brand context and drive subsequent decisions.