seo-audit
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's logic is consistent with its stated purpose of performing technical SEO audits. No malicious obfuscation, exfiltration, or persistence mechanisms were identified.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes external data.
- Ingestion points: Content from web pages,
robots.txt, andsitemap.xmlare ingested into the agent context for analysis in the workflow described inSKILL.md. - Boundary markers: Absent. The instructions do not define clear delimiters or warnings to ignore instructions embedded within the metadata or structured data being audited.
- Capability inventory: The skill uses browser automation (implied by Playwright) and network requests to fetch site-level files and verify URLs, and it generates CSV files.
- Sanitization: Not specified. While JSON-LD is checked for valid JSON syntax, the text content within tags is not explicitly sanitized before processing.
Audit Metadata