The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to construct and execute shell commands using a user-supplied variable (rule-name). Specifically, the instruction nx run-many -t lint:eslint -- --rule "<rule-name>: error" --fix interpolates user input into a shell command, which is a classic injection vector if the agent does not sanitize the input.
[COMMAND_EXECUTION]: The skill performs significant repository modifications using git add -A and git commit. While intended for its core purpose of lint fixing, this provides the agent with high-privilege access to the project's source control.

batch-lint-cleanup