google-ads-ecommerce
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides implementation instructions for the Google Tag (gtag.js), which is loaded from Google's official content delivery network.
- [INDIRECT_PROMPT_INJECTION]: The skill defines evaluation tasks where the agent processes external data structures, such as order logs and product catalogs, to generate tracking scripts or XML feeds.
- Ingestion points: Mock data files inputs/order-example.json and inputs/products.json are used as inputs for the agent's tasks within the evaluation subfolders.
- Boundary markers: The skill does not provide specific delimiters or instructions to ignore potential commands embedded within the input data.
- Capability inventory: The skill targets agents with extensive capabilities including file system access and command execution (e.g., claude-code, cursor).
- Sanitization: No explicit sanitization or validation logic is prescribed for handling external input data before processing.
Audit Metadata