The Agent Skills Directory

[COMMAND_EXECUTION]: The skill employs standard Git commands such as git worktree, git merge, and git branch to manage development workflows. These actions are aligned with the skill's stated purpose.
[INDIRECT_PROMPT_INJECTION]: The skill interacts with external repository data, which creates a potential surface for indirect prompt injection. Ingestion points: The skill reads repository-specific setup instructions and lockfiles (SKILL.md). Boundary markers: There are no specific instructions to ignore malicious content within the repository files. Capability inventory: The skill has the capability to execute Git commands and modify the filesystem (SKILL.md). Sanitization: No specific sanitization or validation of repository content is mentioned.

use-worktrees