google-meta-ads-ga4-mcp
Warn
Audited by Snyk on May 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). This skill requires connecting at runtime to a hosted MCP server via the configured endpoint (YOUR_MCP_ENDPOINT_URL), and that remote URL is a required runtime dependency that supplies tools/responses which can directly control the agent's prompts/behavior.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 1.00). The skill explicitly provides read-write ad platform APIs that create and modify campaigns, ad sets, bids, and budgets. Examples: create_search_campaign accepts budget_amount_micros; meta_create_ad_set accepts daily_budget and bid_amount; update_campaign is used to change daily_budget_micros; tools to resume/pause campaigns and pause keywords. These are direct APIs to change ad spend and bidding (not just read-only), so the skill grants direct financial execution authority over advertising budgets.
Issues (2)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata