The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes TerminalToolkit to grant the AI agent shell access, enabling it to read source code and perform in-place edits on documentation files as part of its core functionality.
[COMMAND_EXECUTION]: The accompanying automation script auto_sync_docs_with_chatagent.py executes git commands and local Python scripts via subprocess calls to manage the documentation mapping and state verification. These calls use hardcoded arguments without a shell, which is a secure practice.
[PROMPT_INJECTION]: This skill is vulnerable to indirect prompt injection as it ingests untrusted data from .mdx documents and Python source files. No explicit boundary markers are used in the prompt construction. The agent possesses significant capabilities through the TerminalToolkit (shell access). However, the script implements a sanitization-equivalent verification step using _git_status_paths, which detects and prevents unauthorized modifications to the repository after the agent completes its task.

docs-incremental-update