The Agent Skills Directory

[SAFE]: The skill provides legitimate technical instructions for reverse engineering hypervisor environments using standard diagnostic utilities (cpuid, grep, modprobe) and industry-standard analysis platforms (Ghidra, IDA, QEMU).
[INDIRECT_PROMPT_INJECTION]: The skill inherently possesses an indirect prompt injection surface as its primary function is to ingest and analyze untrusted hypervisor binaries, driver modules, and configuration files.
Ingestion points: Analysis of binary files (VT-x/SVM samples) and configuration scripts (.cell, XM_CF, vdev configs) across all referenced modules.
Boundary markers: Not explicitly defined for the data being analyzed.
Capability inventory: The skill uses shell commands for environment setup and diagnostics, as well as external reverse engineering tools.
Sanitization: Not present; the skill assumes the agent will perform standard static and dynamic analysis on provided samples.

re-hypervisor