The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes local command-line tools, specifically git and the GitHub CLI (gh), to perform branch operations and link issues. It executes commands such as gh issue develop and git checkout -b using parameters derived from user input.
[PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface by processing untrusted user input to form command arguments. This is documented according to the mandatory evidence chain:
Ingestion points: User-provided branch descriptions and issue numbers are captured and processed as described in SKILL.md.
Boundary markers: No explicit delimiters or boundary markers are defined to isolate user input within the command strings.
Capability inventory: The skill possesses the capability to execute shell commands (git and gh) on the local system.
Sanitization: rules/branch-naming.md enforces lowercase conversion, replaces spaces/underscores with hyphens, and rejects specific shell and git-sensitive characters including ~, ^, :, ?, *, [, ], \, @{, and ... This significantly reduces the risk of malicious command manipulation.

create-branch