pwn-chain

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill is a detailed, step‑by‑step exploit development and kernel pwn playbook (RCE, privilege escalation via commit_creds/modprobe_path, persistence techniques and remote exploit stabilization) that enables deliberate unauthorized system compromise and is high risk for malicious abuse.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill's bootstrap/check script explicitly performs git clone and then runs fetched installers (e.g., "git clone https://github.com/niklasb/libc-database && ./get", "git clone https://github.com/pwndbg/pwndbg && ./setup.sh", "git clone https://github.com/bata24/gef"), so these GitHub URLs are fetched and executed at runtime and are required dependencies for the skill.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 1.00). 该 skill 明确要求在本地执行和安装工具（apt/pip/gem/clone/setup）、并包含内核利用与提权步骤（commit_creds、modprobe_path、改 init 脚本等），直接鼓励修改系统状态并获取 root，存在高风险。