seo-audit
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes several internal Python scripts, including
scripts/fetch_page.py,scripts/google_auth.py,scripts/backlinks_auth.py,scripts/drift_history.py, andscripts/google_report.py. These scripts are used for crawling, checking API credentials, and generating report files. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external websites (up to 500 pages). This data ingestion represents a potential attack surface.
- Ingestion points: Website HTML retrieved via
scripts/fetch_page.pyis processed in subagent workflows. - Boundary markers: No specific boundary markers or instructions are defined to separate crawled content from agent instructions.
- Capability inventory: The skill has network access for crawling, performs file writes for caching and reports, and executes Python scripts.
- Sanitization: There is no evidence of sanitization or filtering of the external website data before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill references integrations with well-known services such as Google APIs (CrUX, GSC, GA4) and DataForSEO to enrich the audit data. These interactions are standard for SEO auditing tools.
Audit Metadata