hmos-multidevice-screen-window-size

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is entirely focused on HarmonyOS UI development tasks such as responsive layouts, breakpoint systems, and window listening mechanisms.
  • [DATA_EXFILTRATION]: No network operations or commands accessing sensitive user data were found. The skill operates locally within the project environment.
  • [REMOTE_CODE_EXECUTION]: The skill does not download or execute external scripts. It relies on standard HarmonyOS Kits (@kit.ArkUI, @kit.AbilityKit) which are local to the HarmonyOS SDK environment.
  • [COMMAND_EXECUTION]: The instructions do not contain arbitrary or high-risk command execution. Standard build commands (hvigorw) are mentioned only within the metadata of test case JSON files for validation purposes.
  • [PROMPT_INJECTION]: The instructions are purely functional and do not attempt to bypass safety filters, extract system prompts, or override agent constraints.
  • [OBFUSCATION]: All content, including code samples and documentation, is provided in clear, plain text without hidden characters or encoded strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 10:16 AM
Security Audit — agent-trust-hub — hmos-multidevice-screen-window-size