landmark-one-main
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: The skill is entirely documentation-based, providing references to established accessibility standards from W3C and MDN. All external links are to trusted domains.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external HTML content (ingestion point: SKILL.md). Although it lacks explicit boundary markers or sanitization, it does not possess any dangerous capabilities like file writing or network access, making the analysis surface safe.\n- [NO_CODE]: There are no scripts, binaries, or configuration files that execute logic, significantly reducing the attack surface.
Audit Metadata