The Agent Skills Directory

[SAFE]: The skill implements a local monitoring mechanism to protect the integrity of test files. No malicious patterns such as prompt injection, data exfiltration, or unauthorized network activity were detected.
[COMMAND_EXECUTION]: The skill executes a local shell script (scripts/block-test-edits.sh) as part of its PreToolUse hook. This script is bundled with the skill and performs non-intrusive string matching on file paths to enforce the edit-blocking policy. This is a legitimate and safe use of command execution for the skill's stated purpose.

freeze-tests