The Agent Skills Directory

[COMMAND_EXECUTION]: The skill directly interpolates the $ARGUMENTS variable into several shell commands, including cargo test, cargo clippy, cargo doc, and git log. A malicious user could provide a crate name containing shell metacharacters (e.g., ;, &&, |, or backticks) to execute arbitrary commands on the system.
[COMMAND_EXECUTION]: Multiple gates (Gate 1, 2, 6, 7, 9, 12) use the user-provided crate name in file paths and grep commands without validation, which can be exploited to read or verify the existence of sensitive files outside the intended directories.

gate-check