uit-content-identity-web

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill serves as a guide for using UI components (Text, Icons, Avatars, Badges) within the Meta Ray-Ban Display ecosystem. All external resource references, such as the @wearables-ui-toolkit/icons package, are standard vendor-specific libraries.
  • [COMMAND_EXECUTION]: The skill includes a local utility script, scripts/find-filled-icon.mjs, which is used to query an icon manifest.
  • The script reads a local JSON manifest from the @wearables-ui-toolkit/icons package.
  • It performs string matching against user-provided search terms and outputs recommended import statements to the console.
  • It does not perform network operations, access sensitive user data, or execute secondary subprocesses.
  • [INDIRECT_PROMPT_INJECTION]: The icon search script provides a surface for processing user-supplied data.
  • Ingestion points: Command-line arguments in scripts/find-filled-icon.mjs via process.argv.slice(2).
  • Boundary markers: None (script-based processing).
  • Capability inventory: The script is limited to reading the local toolkit manifest and logging to stdout. It has no capabilities for file writing, network access, or command execution.
  • Sanitization: Inputs are normalized to lowercase and trimmed before being used for string-based scoring.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 06:17 PM