21-audit-ads-performance
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a diagnostic tool for advertising accounts, providing checklists for Meta Ads, TikTok Ads, Google Ads, and Zalo Ads without executing harmful code.
- [SAFE]: Data ingestion via MCP or CSV exports is handled as passive data, with explicit instructions to the agent to avoid treating tool output as executable commands, mitigating indirect prompt injection risks.
- [SAFE]: All external URLs and platform integrations (e.g., Meta Official MCP) target legitimate or vendor-controlled domains without signs of typosquatting or phishing.
- [SAFE]: No obfuscation (Base64, zero-width characters, or homoglyphs) or persistence mechanisms were found in the skill body or references.
Audit Metadata