md-section
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes arbitrary HTML data provided by users which serves as a potential surface for indirect prompt injection. However, the skill explicitly instructs the agent to strip external scripts, stylesheets, and dangerous HTML attributes (e.g., onclick, onerror) during the conversion process, which significantly mitigates the risk of executing malicious content in the resulting output.
Audit Metadata