paw-mkt-video

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

• Third-party content exposure detected (high risk: 0.90). Flagged: the skill's workflow (SKILL.md Response Protocol and references/shared-patterns.md "Context C — Live Website URL Audit" and the agent-browser examples) explicitly instructs the agent to open, fetch, and read public URLs (e.g., LinkedIn, Twitter/X, Facebook Ads Library via agent-browser or WebFetch) and to use that live page content as the working source of truth for strategy, so untrusted third‑party content is ingested and can materially influence decisions and actions.