seo-internal-linking
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a Python script
scripts/site_crawl.pythat the agent is instructed to execute to audit site architecture and detect orphan pages. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external websites (via the crawler) and local Obsidian vault notes to generate SEO recommendations.
- Ingestion points: Content from crawled websites in
scripts/site_crawl.pyand local.mdnotes in the project directory as described inSKILL.md. - Boundary markers: None identified in instructions or scripts.
- Capability inventory: The skill can perform network requests and read local filesystem content.
- Sanitization: The script does not appear to sanitize or escape HTML content (titles, H1s, etc.) before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The
scripts/site_crawl.pyscript makes network requests to fetch content, sitemaps, and robots.txt files from arbitrary domains provided by the user. The script explicitly disables SSL certificate verification (ssl.CERT_NONE), which exposes the agent to intercepted or modified traffic. - [DYNAMIC_EXECUTION]: The crawler script dynamically loads an external Python module from a relative path outside its own directory structure.
- Evidence: The
load_auditorfunction inscripts/site_crawl.pyusesimportlib.utilto load../../seo-geo-audit/scripts/seo_audit.py.
Audit Metadata