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, and sitemap.xml are ingested into the agent context for analysis in the workflow described in SKILL.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
Risk Level
SAFE
Analyzed
Aug 1, 2026, 10:40 PM
Security Audit — agent-trust-hub — seo-audit