The Agent Skills Directory

[COMMAND_EXECUTION]: The helper script scripts/markdown_helper.py executes system commands to interact with Git.
The function get_git_commits uses subprocess.run to execute the git log command for extracting commit metadata used in changelog generation.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: The skill reads Markdown files via scripts/markdown_helper.py and Git commit history to generate tables of contents and changelogs.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard instructions embedded within the document content or commit messages during processing.
Capability inventory: The skill has the capability to read and write files locally and execute shell commands via the Git CLI.
Sanitization: The script extracts text using regular expressions but does not perform sanitization or validation of the content to prevent instruction injection before the agent processes it.

markdown-pro