The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute standard git commands, including git fetch, git worktree add, and git rev-parse. These operations are routine for local repository management and align with the skill's stated purpose.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from Linear URLs and issue descriptions. To mitigate risks, the instructions include a robust 'slugification' process that requires the agent to strip special characters such as backticks, parentheses, and quotes before using the input in shell commands. This sanitization significantly reduces the surface area for indirect injection via issue metadata.

linear-worktree