meta-ads

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

• Third-party content exposure detected (low risk: 0.10). The agent skill references Firecrawl (firecrawl_screenshots_create, firecrawl_branding_extract) and web fetching (web_pages_fetch) to ingest external web pages and outsider-authored site content.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (high risk: 1.00). The skill is designed for planning, creating, and managing Meta (Facebook + Instagram) advertising campaigns via MCP tools. According to the guidelines, managing Ad Spend Budgets (specifically APIs to update the budget) is considered Direct Financial Execution (Risk: 1). This skill explicitly lists ad budget controls (BUDGETS IN CENTS, budget guards, automated rules for budgets, and campaign updates affecting spend) under its core capabilities and toolsets (meta_ads_campaign_update, meta_ads_adset_update, etc.).