clarify

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or behaviors were identified. The skill follows security best practices by instructing the agent to escape untrusted content and use ephemeral storage for temporary files.
  • [PROMPT_INJECTION]: The skill processes untrusted artifacts, which is a potential surface for indirect prompt injection. It explicitly mandates HTML-escaping of all verbatim content to mitigate injection and XSS risks in generated artifacts.
  • Ingestion points: Target artifacts from user input or session history.
  • Boundary markers: Concluding 'lens' disclaimer.
  • Capability inventory: Generates HTML artifacts and temporary local files.
  • Sanitization: Explicit HTML-escaping of all verbatim text content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 07:56 PM
Security Audit — agent-trust-hub — clarify