The Agent Skills Directory

[SAFE]: No malicious patterns such as prompt injection, credential theft, or unauthorized data exfiltration were found in the skill's instructions.
[COMMAND_EXECUTION]: The skill provides a bash script for the agent to use when verifying drift between Starlark blocks. The script uses standard utilities (sed, diff) to extract and compare fenced code blocks from user-provided files.
[EXTERNAL_DOWNLOADS]: The skill does not initiate any external network requests or downloads. It relies on platform-native skill invocations for interview and review processes.

policy-algebra