verify

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 1.00). This is a direct network shell script (install.sh) that the repo itself warns will be curl|bash'd and can overwrite local binaries, so it is a high-risk installer that should not be executed.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The repo documents a script that performs direct remote code execution via "curl ... | bash" (and PowerShell equivalent), can overwrite local binaries, and includes an intentional bypass to install arbitrary CLI versions — indicating high-risk remote-exec / supply-chain behavior that could be abused.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill's download_cli.py explicitly shells out to "curl https://claude.ai/install.sh | bash", which is a runtime fetch of remote code that is then executed, so the external URL directly controls executed code.