The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes Python scripts (scripts/probe_ripgrep.py, scripts/validate.py, scripts/test_skill.py) that utilize subprocess.run to execute local commands. These operations are limited to running rg for behavior verification and sh for syntax checking. These scripts use safe argument list passing (preventing shell injection) and target a temporary local corpus or the skill's own files.
[EXTERNAL_DOWNLOADS]: The skill references official source code and documentation for ripgrep (github.com/BurntSushi/ripgrep). These references are informational and do not involve automated execution of untrusted remote code.
[PROMPT_INJECTION]: The instructions do not contain any patterns attempting to bypass agent safety filters or override system behavior. The guidelines correctly instruct the agent on how to handle user-provided strings using literal search flags and proper shell quoting.
[SAFE]: The skill adheres to security best practices by recommending literal matching (-F) to avoid unintended regex behavior and emphasizing the use of single quotes for patterns to prevent shell expansion issues.

ripgrep