The Agent Skills Directory

[SAFE]: The skill includes a Python script (checker/check.py) intended for auditing local project directories for conformance with security and structural standards.\n- [SAFE]: Command execution is implemented using subprocess.run with a fixed list of arguments, specifically calling the git binary to query tracked files in the target repository. This is restricted to read-only operations for auditing purposes.\n- [SAFE]: YAML file processing is performed using yaml.SafeLoader (via the _Loader subclass), which prevents the execution of arbitrary code during the parsing of configuration files.\n- [SAFE]: The skill aims to improve security by detecting hardcoded credentials, unpinned Docker images, and missing healthchecks in external repositories being analyzed by the agent.\n- [SAFE]: No evidence of prompt injection, data exfiltration, or persistence mechanisms was found in the provided files.

typo3-site-conformance