google-ads-ad-extension-audit
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely instructional and does not contain any executable scripts, shell commands, or network requests.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze external Google Ads data, which represents an ingestion surface for untrusted data. However, the risk is negligible as the skill lacks active capabilities such as file system writes, network exfiltration, or command execution that could be exploited by an injection payload.
- [DATA_EXPOSURE]: The skill references an internal configuration file
.agents/product-marketing-context.md. This is a standard practice for agent context management and does not involve accessing sensitive system credentials or private user data. - [METADATA_POISONING]: All metadata fields (name, description, version) are consistent with the content and do not contain deceptive instructions or injection attempts.
Audit Metadata