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.py script retrieves search queries directly from the Google Ads API.\n
  • Boundary markers: Output is displayed using the tabulate library 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 .env files via python-dotenv. The skill exclusively uses official Google Ads API endpoints and libraries.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 17, 2026, 07:59 AM
Security Audit — agent-trust-hub — google-ads