meta-ads

Warn

Audited by Snyk on Apr 17, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and processes user-generated content from Meta's Graph API (e.g., curl calls to https://graph.facebook.com/v22.0/... for ad accounts, campaigns, ads, insights and paging.next), so returned third‑party fields and URLs are read/interpreted by the agent and could materially influence actions.

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

  • Direct money access detected (high risk: 1.00). The skill is explicitly the Meta Marketing API and includes endpoints and examples to create, update, and delete campaigns/ad sets and to set budgets and bid amounts. Examples show POST requests that modify "daily_budget", "lifetime_budget", "bid_amount", and campaign "status" (activate/pause). Account-level fields include "balance", "amount_spent", and "spend_cap". This is a purpose-built API to manage ad spend and budgets (i.e., directly change where money is allocated and enable spending), which matches the "Managing Ad Spend Budgets" criterion for Direct Financial Execution.

Issues (2)

W011
MEDIUM

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

W009
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 17, 2026, 04:45 PM
Issues
2