The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to perform repository operations using shell commands.
Evidence: SKILL.md contains instructions for executing git worktree add, git fetch, git rev-parse, and direct modifications to the .gitignore file.
[PROMPT_INJECTION]: The skill contains an indirect prompt injection attack surface where untrusted data is incorporated into shell commands.
Ingestion points: SKILL.md directs the agent to "Choose a meaningful branch name from the work description", where the description is external user input.
Boundary markers: The skill does not provide delimiters or instructions to ignore embedded commands within the work description.
Capability inventory: The skill executes subprocesses using the git worktree add -b <branch-name> ... command found in SKILL.md.
Sanitization: No sanitization or validation logic is specified for the branch name before its interpolation into the shell command.

ce-worktree