google-ads

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the Google Ads API, specifically user-generated search terms. This data represents a surface for indirect prompt injection where malicious instructions embedded in search queries could potentially influence the agent's behavior.
  • Ingestion points: The skill ingests search_term_view data and campaign metadata through the Google Ads API as described in the audit workflows and REFERENCE.md.
  • Boundary markers: No specific delimiters or 'ignore' instructions are defined in the skill to isolate external API data from the agent's system prompt or instructions.
  • Capability inventory: The skill possesses the capability to both read from and modify Google Ads account data, including pausing keywords, adjusting budgets, and modifying bid strategies via the google-ads library.
  • Sanitization: There is no evidence of string sanitization, filtering, or validation for the data ingested from the API within the provided files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 08:54 PM
Security Audit — agent-trust-hub — google-ads