The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes several Git and Bash commands to analyze repository state and perform branch renaming. Specifically, it uses git branch -m to modify the local repository state, and git diff and git log to read information.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the Git environment to generate output, which could be influenced by malicious content in commit messages or file names.
Ingestion points: The skill reads commit messages via git log and file paths/stat information via git diff as seen in the workflow sections of SKILL.md.
Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within the analyzed Git data provided in the skill instructions.
Capability inventory: The skill possesses the capability to execute shell commands and modify local Git configuration via git branch -m.
Sanitization: The skill defines a robust sanitization process for the generated branch description, including conversion to lowercase, removal of special characters (leaving only a-z0-9-), and a 20-character length limit. This effectively prevents typical command injection payloads from being executed during the renaming process.

rename-branch