pp-facebook-marketplace

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

• Third-party content exposure detected (high risk: 0.90). This skill directly fetches and ingests user-generated Facebook Marketplace content (e.g., via commands like "marketplace_search", "listing get", "marketplace browse_feed", and "inbox seller_threads" described in SKILL.md), which the agent is expected to read and act on (matches, draft, reply), so untrusted third-party content could influence tool decisions.