google-ads-transparency-api
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends the installation of the
scaviopackage via standard package managers (pip and npm) to interface with the vendor's API. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data from the Google Ads Transparency Center, representing an indirect prompt injection surface.
- Ingestion points: Ad creatives and advertiser metadata are ingested from the
api.scavio.devendpoint. - Boundary markers: Instructions explicitly guide the agent to 'Only return API data' and to quote disclosures verbatim.
- Capability inventory: The skill uses network requests via the
scavioSDK or standard HTTP libraries to fetch data. - Sanitization: The documentation provides specific rules for reporting data ranges and handling missing EEA data to prevent misinterpretation of ingested content.
Audit Metadata