The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute local system tools including gdb, lldb, and qemu-system binaries for the purpose of process debugging and analysis. These commands are restricted to the local workspace and are central to the skill's diagnostic function.- [PROMPT_INJECTION]: The skill defines a workflow for analyzing external data such as guest logs, trace events, and debugger transcripts. This creates an indirect prompt injection surface where maliciously formatted log data could potentially influence agent reasoning, although this is a common and managed risk for diagnostic agents.- [SAFE]: The skill includes a specific safety procedure to prevent accidental data exposure by modifying the repository's local Git exclude file (.git/info/exclude) to ensure that logs, temporary scripts, and build artifacts are not committed to source control.

qemu-debug