21-audit-ads-performance

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed for auditing advertising performance, and all instructions are strictly related to evaluating account setup, creative quality, and tracking integrity.
  • [EXTERNAL_DOWNLOADS]: The skill references official and well-known Model Context Protocol (MCP) endpoints, such as those from Meta (Facebook), Google, and reputable third-party providers like Pipeboard. These references are documented neutrally as standard tools for fetching advertising metrics and do not involve untrusted code execution.
  • [DATA_EXFILTRATION]: No evidence of unauthorized data exfiltration was found. The skill processes advertising data (either pasted by the user or pulled via authorized MCP integrations) solely for the purpose of generating a performance audit report.
  • [PROMPT_INJECTION]: The instructions do not contain any patterns intended to bypass AI safety filters, override system instructions, or extract system prompts.
  • [COMMAND_EXECUTION]: The skill does not contain any shell commands, script executions, or dynamic context injection patterns. The provided GAQL (Google Ads Query Language) is a data query template and is not executable code within the skill context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 06:53 PM
Security Audit — agent-trust-hub — 21-audit-ads-performance