pp-google-ads
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation provides instructions for installing the necessary CLI and MCP server using npx and go install. These commands fetch code from the vendor's own repositories (github.com/mvanhorn/printing-press-library and @mvanhorn/printing-press-library).
- [COMMAND_EXECUTION]: The skill executes the google-ads-pp-cli binary to interact with the Google Ads API through the shell.
- [DATA_EXFILTRATION]: The CLI tool includes a built-in feature to deliver command output to external endpoints using the --deliver webhook: flag. This allows for the transmission of retrieved Google Ads data to remote services.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes data from external sources.
- Ingestion points: Data retrieved from the Google Ads API via commands like customers-google-ads search and audience-insights.
- Boundary markers: The skill instructs the agent to use the --agent flag, which ensures results are returned in structured JSON format.
- Capability inventory: The skill can mutate Google Ads resources (create/update/remove), write output to local file paths using the file: sink, and POST data to external URLs via the webhook: sink.
- Sanitization: No explicit sanitization or filtering of API data is described in the skill instructions.
Audit Metadata