google-search-console

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from Google Search Console and PageSpeed Insights APIs, which could theoretically contain malicious instructions (e.g., within search queries or website content).
  • Ingestion points: API responses containing site details, analytics queries, and Lighthouse audit results are processed in src/gsc/analytics.py, src/gsc/inspect_url.py, and src/gsc/pagespeed.py.
  • Boundary markers: The skill outputs data in JSON format, providing a structured boundary, though it does not explicitly sanitize string values for potential prompt injection patterns.
  • Capability inventory: The skill has the ability to write to the local file system (config/credentials) and modify Search Console properties (adding sites, managing sitemaps).
  • Sanitization: Uses standard JSON serialization for all outputs to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 03:21 AM
Security Audit — agent-trust-hub — google-search-console