The Agent Skills Directory

[SAFE]: The skill provides instructions for utilizing the ast-grep CLI for syntax-aware code searches. No malicious behavior, obfuscation, or unauthorized data access patterns were detected.
[COMMAND_EXECUTION]: The skill utilizes the Bash tool to run search and debugging commands. The provided documentation explicitly guides the agent on safe shell quoting practices (such as using PowerShell here-strings and POSIX single quotes) to prevent command construction errors.
[PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted repository data, which constitutes an indirect prompt injection surface. However, the risk is significantly mitigated by the skill's mandatory 'Workflow' which requires the creation of tiny fixtures and validation of rules in isolation before scanning the main repository.
[EXTERNAL_DOWNLOADS]: The skill assumes that necessary tools like ast-grep or rg are already present in the execution environment. It does not attempt to download or execute remote scripts or unverified third-party packages.

ast-grep