seo-audit
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions and associated reference files do not contain any malicious patterns, such as credential theft, unauthorized data access, or dangerous command execution. The logic is strictly focused on providing SEO recommendations based on best practices.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external websites via
web_fetchorcurlas part of its primary SEO auditing function. - Ingestion points: External website content retrieved during audits (mentioned in
SKILL.md). - Boundary markers: Not explicitly defined in the instructions to separate data from prompts.
- Capability inventory: Analysis and report generation only; no hazardous system commands or file modifications are enabled.
- Sanitization: The instructions do not specify sanitization for the fetched HTML content.
Audit Metadata