google-ads-scripts
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXFILTRATION]: The skill includes templates that use
MailApp.sendEmail()andSpreadsheetApp.openByUrl()to export campaign data. These are standard features for the intended use case of alerting and reporting but represent a mechanism for moving account data to external endpoints defined by the user. - [INDIRECT_PROMPT_INJECTION]: The 'Search Term Mining' template in
SKILL.mdingests untrusted strings from search query reports. - Ingestion points:
AdsApp.reportretrieves data from theSEARCH_QUERY_PERFORMANCE_REPORTtable. - Boundary markers: Absent; raw query strings are processed directly from the report rows.
- Capability inventory: The script has the capability to modify account settings via
negList.addNegativeKeyword()and output data to logs. - Sanitization: The script uses regex tests (
.test(query)) to identify specific patterns before adding them as exact-match negative keywords, which limits the impact of potentially malicious search strings.
Audit Metadata