The Agent Skills Directory

[SAFE]: The skill instructions focus on standard kernel build procedures using local tools like make, cpio, and git. No malicious patterns such as credential exfiltration, obfuscation, or unauthorized network operations were detected.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from the local Linux source tree and Git configuration (e.g., include/config/kernel.release, git rev-parse) to determine the build environment and kernel release version. While this constitutes an ingestion point for untrusted data, it is a necessary part of the skill's primary purpose for kernel building and testing. The risk is minimized as the data is used within a structured build context.

qemu-kernel-build