google-ads
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing external user-generated data.\n
- Ingestion points: The
scripts/search_terms_report.pyscript retrieves search queries directly from the Google Ads API.\n - Boundary markers: Output is displayed using the
tabulatelibrary without specific delimiters or contextual instructions to ignore commands within the data.\n - Capability inventory: The agent has broad capabilities to create, update, and pause campaigns, which could be misused if influenced by malicious data.\n
- Sanitization: No filtering or sanitization of search query content is performed before presentation.\n- [SAFE]: Credential handling follows standard security practices by loading secrets from
.envfiles viapython-dotenv. The skill exclusively uses official Google Ads API endpoints and libraries.
Audit Metadata