external-links

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructional content for auditing external link quality and security. It correctly recommends the use of rel="noopener noreferrer" for security and standard SEO link attributes.
  • [PROMPT_INJECTION]: The skill instructs the agent to process external web content (parsing HTML <a> tags). While this creates a surface for indirect prompt injection, it is inherent to the skill's intended purpose of SEO auditing and does not include unsafe interpolation or execution instructions. Evidence: SKILL.md instructs to 'Parse all elements with external URLs'.
  • [EXTERNAL_DOWNLOADS]: The skill references documentation and research from well-known and trusted sources including Google (web.dev), Mozilla (MDN), and WebAIM. These references are documented neutrally and serve legitimate educational purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 12:29 AM
Security Audit — agent-trust-hub — external-links