draft-ia
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious prompt injection patterns were detected. The instructions are strictly focused on providing a persona-driven UX design workflow for sitemaps and content hierarchy.
- [SAFE]: The skill does not contain hardcoded credentials, access sensitive system files, or attempt to exfiltrate data. Network-capable tools like 'WebFetch' and 'WebSearch' are listed in the configuration but are not used in the instructions for suspicious activities.
- [SAFE]: No obfuscation techniques, such as Base64 encoding, zero-width characters, or homoglyphs, were found in the skill files.
- [SAFE]: The skill utilizes a vendor-specific command '/atlas-report' for generating analysis outputs, which is consistent with the infrastructure provided by the author 'tonone-ai'.
- [SAFE]: While the skill ingests external data such as 'product descriptions' and 'Helm briefs', it does not possess dangerous capabilities that create a high-risk indirect prompt injection surface in this context.
Audit Metadata