google-ads-audit

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill has a vulnerability surface for indirect prompt injection as it processes untrusted external data from a Google Ads account, specifically search terms and ad asset text.
  • Ingestion points: The skill retrieves data from the Google Ads API using GAQL queries for search_term_view.search_term and asset.text_asset.text (RSA assets) within the SKILL.md file.
  • Boundary markers: The skill uses structured templates located in drafts/templates/ and a specific 'Audit Order' to process data, which provides some implicit boundaries for the agent's reasoning.
  • Capability inventory: The skill is capable of writing multiple files to the local file system (e.g., workspace/ads/drafts/, workspace/ads/findings.md, workspace/ads/negatives.md) and reading local reference markdown files.
  • Sanitization: The instructions do not explicitly define sanitization or filtering for the external content retrieved via SQL queries before it is used to generate reports and drafts.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 12:02 PM
Security Audit — agent-trust-hub — google-ads-audit