weekly-account-auditor
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed for read-only analysis of Google Ads data. It includes multiple guardrails that explicitly forbid making changes to the advertising account, such as pausing campaigns or scaling budgets. No malicious patterns, obfuscation, or unauthorized data exfiltration methods were detected.
- [SAFE]: The skill processes external data from Google Ads exports and MCP connections. Ingestion points: User-pasted Google Ads exports and live MCP account metrics. Boundary markers: The skill instructs the agent to confirm account details and date ranges before interpretation, though no explicit XML-style delimiters are used. Capability inventory: Read-only access to Google Ads MCP; no file-write, network, or command execution capabilities. Sanitization: None identified. The risk of indirect prompt injection is minimal given the lack of write or network capabilities.
Audit Metadata