google-ads-audit
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill incorporates an attack surface for indirect prompt injection by ingesting data from external websites during the business context discovery phase.
- Ingestion points: Content is retrieved from the business homepage, about pages, and landing pages via the
WebFetchtool (documented inreferences/business-context.md). - Boundary markers: The extraction logic does not explicitly define the use of delimiters or instructions to ignore embedded prompts within the crawled web content.
- Capability inventory: The skill utilizes
ads.gaqlParallelfor reading account data,WebFetchfor web access, and filesystem operations to write state to the{data_dir}. - Sanitization: The instructions do not specify a sanitization or validation process for the content retrieved from external URLs before it is processed by the agent.
Audit Metadata