broken-external-links
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill focuses solely on SEO best practices for maintaining outbound link integrity.
- [EXTERNAL_DOWNLOADS]: The skill references documentation and guidelines from well-known and trusted sources, including Frontend Checklist and Google Search Central.
- [DATA_EXPOSURE_AND_EXFILTRATION]: Activities are limited to verifying the HTTP status codes of external links. No sensitive local data, environment variables, or credentials are accessed.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze rendered HTML to identify broken links. While this involves processing external data, the instructions are for analytical purposes only and do not involve executing content or unsafe interpolation. Evidence:
- Ingestion points: Rendered HTML and HTTP response headers (SKILL.md, references/rule.md)
- Boundary markers: None present
- Capability inventory: No subprocess calls, file-write operations, or network exfiltration patterns across the analyzed files
- Sanitization: Not applicable as the data is analyzed for link status rather than interpreted as instructions
Audit Metadata