pp-google-search-console
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [DATA_EXFILTRATION]: The skill implements an
--deliver webhook:<url>feature that enables the agent to POST command results to arbitrary network endpoints. While this is a functional capability for routing data, it provides a mechanism for exfiltrating sensitive search performance data to unauthorized external servers. - [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it processes data from external sources and local files without explicit boundary markers.
- Ingestion points: The skill reads performance data from the Google Search Console API and processes local batch files via the
--fileargument. - Boundary markers: The instructions do not define delimiters or specific instructions for the agent to ignore content that might be embedded within the search data or ingested files.
- Capability inventory: The skill has the ability to write files to the local system (
--deliver file:<path>) and perform network operations via webhooks. - Sanitization: No sanitization or validation protocols are described for the data retrieved from external APIs or local text files.
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing the necessary CLI binary from the developer's infrastructure.
- Fetches tools using
npx -y @mvanhorn/printing-press-library. - Provides a fallback installation method via
go install github.com/mvanhorn/printing-press-library/library/marketing/google-search-console/cmd/google-search-console-pp-cli@latest.
Audit Metadata