The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes system commands and local scripts. It runs scripts/finish-branch.sh to perform git operations and executes project-defined test suites (e.g., npm test, pytest, cargo test) during the pre-finish phase as described in references/gitflow-finish-pipeline.md.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface by ingesting untrusted data from the repository, such as git commit messages for changelog generation and project manifest files to identify test commands.
Ingestion points: Git commit history (read via git log in references/changelog-generation.md) and project configuration files (read in references/gitflow-finish-pipeline.md).
Boundary markers: No specific delimiters or instructions (e.g., "ignore embedded instructions") are used to separate the ingested commit data from the agent's processing logic.
Capability inventory: The skill uses git for repository management, bash for script execution and cleanup, and the gh CLI for publishing releases.
Sanitization: There is no evidence of sanitization, escaping, or validation of the commit messages or project configuration data before they are processed or used in shell command contexts.

finish-hotfix