facebook-marketing
Warn
Audited by Snyk on Mar 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to call the Facebook Graph API (e.g., GET /{pageId}/insights, POST /{pageId}/feed, GET /me/accounts and fetching photos via public URLs) to ingest page/post/group data and insights from Facebook — user-generated, public social-media content that the agent is expected to read and that can materially influence posting, moderation, or ad decisions.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 1.00). The skill explicitly includes the Facebook Ads Marketing API and shows steps to create campaigns/ad sets/ads, including references to budget fields (mentions "Then create Ad Set (targeting + budget)" and "Use daily_budget in cents (2000 = $20/day)"). That is a specific API capability to set and manage ad spend (i.e., update budgets/launch campaigns), which qualifies as direct financial execution. While no payment gateway or crypto APIs are present, the Ads Manager budget controls meet the "Managing Ad Spend Budgets" criterion.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata