md-section
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and transform arbitrary HTML layouts provided by users. This input surface could theoretically be used for indirect prompt injection; however, the skill explicitly instructs the agent to strip all
<script>tags, external stylesheets, and dangerous HTML attributes likeonclick,onerror,src, andhref. These sanitization steps are designed to prevent the generation of malicious payloads. - [SAFE]: No evidence of data exfiltration, command execution, or unauthorized network activity was found. The skill does not use obfuscation techniques or external dependencies that would compromise the host environment.
Audit Metadata