underspending-investigation
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The documentation provides
curlcommands to download skill files from the author's public GitHub repository (fourteenwm/ppc-ai-skills). These resources are directly related to the skill's functionality and originate from the recognized author context. - [COMMAND_EXECUTION]: The skill executes a bundled Python script (
investigate_underspend.py) to interface with the Google Ads API. The script usesGoogleAdsClientfor authenticated read-only queries and handles data processing locally to generate diagnostic reports. - [DATA_EXFILTRATION]: The script reads configuration from
google-ads.yamland account mapping fromaccounts.md. This data is used solely for API authentication and account resolution; no patterns were detected that transmit these secrets or account metrics to unauthorized external endpoints. - [PROMPT_INJECTION]: Instructions within
SKILL.mdandrules.mdfocus on maintaining diagnostic integrity and ensuring performance guardrails are met. There are no attempts to override safety filters or manipulate the underlying model's behavior for malicious purposes.
Audit Metadata