seo-audit
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs legitimate SEO auditing by fetching and analyzing external web content. While the ingestion of untrusted data from the web constitutes an attack surface for indirect prompt injection, the skill's design is consistent with standard developer tools and does not exhibit malicious patterns.
- Ingestion points: Data enters the system via
scripts/fetch_page.pywhich retrieves HTML from user-provided URLs. - Boundary markers: No specific delimiters or "ignore previous instructions" warnings are used when processing the crawled HTML content.
- Capability inventory: The skill is capable of running local Python scripts, writing markdown reports (
FULL-AUDIT-REPORT.md,ACTION-PLAN.md), and potentially using Playwright for automated screenshots. - Sanitization: The instructions do not define specific sanitization or filtering logic for the raw content processed by the subagents.
Audit Metadata