The Agent Skills Directory

[SAFE]: No security issues detected. The skill provides diagnostic documentation and code templates for local use by developers. The instructions are focused on troubleshooting Menu component issues in the OpenHarmony ACE Engine.
[COMMAND_EXECUTION]: The skill documents standard shell commands (grep, cat, ninja, build.sh) for users to perform log filtering and component compilation. These are standard development tools and do not involve autonomous or remote execution by the agent.
[INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided bug descriptions and log snippets to categorize issues. While this creates an entry point for untrusted data, the skill acts as a diagnostic advisor for human developers rather than an autonomous actor, and it includes best practices explicitly warning against logging sensitive data.
Ingestion points: User descriptions of Menu component issues (e.g., "Menu width is 0") and log excerpts provided in the chat.
Boundary markers: Not explicitly defined for input processing.
Capability inventory: The skill does not define any allowed-tools or autonomous execution capabilities.
Sanitization: The skill provides guidance on data sanitization by instructing users not to log sensitive information (tokens, user data).

menu-debug