seo-analytics

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external CSV and JSON data exports from Google Search Console, Bing Webmaster Tools, and GA4. This capability introduces a surface for indirect prompt injection where instructions could be embedded within search queries or page data. The skill mitigates this by instructing the agent to treat all user-supplied exports as untrusted data rather than instructions, and by prioritizing aggregate evidence over raw data.
  • [COMMAND_EXECUTION]: The utility script scripts/lib/cli-utils.mjs executes the local gcloud command-line tool using execFileSync to retrieve access tokens. This is a standard and expected behavior for tools that utilize Google's Application Default Credentials for automated authentication.
  • [EXTERNAL_DOWNLOADS]: The skill's fetch scripts perform network operations targeting official API endpoints for Google (googleapis.com) and Bing (ssl.bing.com). These are well-known and trusted technology services essential for the skill's primary purpose of gathering search performance metrics.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 05:07 PM