lynx-a2ui

Pass

Audited by Gen Agent Trust Hub on Nov 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches a dynamic UI catalog from an external source to define valid components and properties.
  • Evidence: SKILL.md (Catalog Source) fetches from https://unpkg.com/@lynx-js/genui/a2ui/dist/catalog.json. This is a vendor-owned resource hosted on a well-known CDN.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface where a compromised or malicious external catalog could attempt to inject instructions into the agent's output.
  • Ingestion points: SKILL.md instructs the agent to fetch and follow a JSON catalog from a remote URL.
  • Boundary markers: The skill instructs the agent to use the catalog as an authoritative, dynamic type definition and provides hard rules for output formatting.
  • Capability inventory: The skill's output is restricted to pure JSON data messages; it lacks capabilities for shell execution, file system modification, or network exfiltration of sensitive data.
  • Sanitization: Instructions explicitly forbid emitting executable code, scripts, event handlers, or HTML tags, mitigating the risk of executing untrusted content.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 16, 2026, 06:08 AM