seo-google

Pass

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes Python scripts via the claude-seo run tool to perform SEO tasks like querying Search Console, running PageSpeed tests, and submitting URLs to the Indexing API. All scripts are documented as part of the local skill package.
  • [EXTERNAL_DOWNLOADS]: Documentation references the google-ads Python package for keyword planning features. This is a legitimate dependency provided by a well-known service (Google).
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface (Category 8) as it ingests data from external URLs and batch files to generate SEO reports.
  • Ingestion points: URL arguments in pagespeed_check.py, crux_history.py, gsc_inspect.py, indexing_notify.py, nlp_analyze.py, and local batch files in gsc_inspect.py and indexing_notify.py.
  • Boundary markers: None identified in the instructional content.
  • Capability inventory: Subprocess execution for Google API interactions and local markdown/PDF report generation via google_report.py.
  • Sanitization: No specific sanitization or escaping mechanisms are documented for the external content before it is processed or reported.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 21, 2026, 09:13 AM
Security Audit — agent-trust-hub — seo-google