seo-audit
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external web content via BrowserOS to perform SEO audits, which is a known attack surface for indirect prompt injection. However, the framework protocols explicitly mitigate this risk.
- Ingestion points: External web content accessed via BrowserOS (SKILL.md).
- Boundary markers: The 'Security & Multi-Agent Hygiene' section defines untrusted inputs as hostile.
- Capability inventory: Use of sequentialthinking and context7 MCP tools, and ExecutionProxy for terminal actions (SKILL.md).
- Sanitization: Mandatory redaction of secrets and PII.
- [SAFE]: The overall skill design is professional, consistent with its stated purpose, and adheres to high standards of security and technical integrity.
Audit Metadata