google-ads-audit
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external API sources which could theoretically contain malicious instructions.\n
- Ingestion points: Account data is fetched from the Google Ads API as shown in the extractAccountData function in SKILL.md.\n
- Boundary markers: No explicit delimiters or boundary markers for external content are visible in the provided implementation snippets.\n
- Capability inventory: The skill's functionality is limited to data retrieval, pattern matching, and report generation. No dangerous capabilities such as arbitrary command execution, network exfiltration to unknown domains, or persistent file system modifications were identified.\n
- Sanitization: The implementation code focuses on audit logic rather than sanitization of external text inputs before processing.
Audit Metadata