frontend-design
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill consists entirely of instructional markdown and a metadata JSON file. No executable scripts, binaries, or source code files are included, precluding direct execution risks.- [EXTERNAL_DOWNLOADS] (SAFE): The metadata references a source URL from a trusted GitHub organization ('anthropics'). This falls under the TRUST-SCOPE-RULE as a low-risk reference to an authoritative repository.- [PROMPT_INJECTION] (SAFE): Instructional emphasis markers such as 'CRITICAL' and 'IMPORTANT' are used solely to reinforce design best practices. There are no attempts to bypass safety filters, extract system prompts, or hijack agent behavior.- [DATA_EXFILTRATION] (SAFE): No sensitive file paths, hardcoded credentials, or network transmission patterns were identified.- [INDIRECT_PROMPT_INJECTION] (SAFE): While the skill defines how to process user UI requirements, it lacks any internal capability (such as file-writing or subprocess execution) that could be exploited via malicious input.
Audit Metadata