workflow-technical-watch
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides a structured methodology for using specialized SEO tools to monitor technical site health.
- [PROMPT_INJECTION]: The skill processes data from external sources (crawled URLs and sitemaps), which constitutes a potential surface for indirect prompt injection.
- Ingestion points: Data enters the workflow via the
startUrlandsitemapsparameters provided to theseo_run_reporttool inSKILL.md. - Boundary markers: Present; the skill instructions require the agent to independently inspect nested crawl and index outputs and distinguish between various technical states.
- Capability inventory: Network access for crawling and URL inspection is performed through the
seo_run_reporttool. - Sanitization: The workflow focuses on extracting technical metadata (indexing status, redirect chains, and crawl errors) rather than rendering or executing arbitrary page content.
Audit Metadata