The Agent Skills Directory

[SAFE]: No security issues were detected. The skill is composed of documentation and configuration files used to structure AI agent behavior for a specific task.
[COMMAND_EXECUTION]: The skill does not contain any shell commands or subprocess execution patterns. It uses a disable-model-invocation: true flag, which further limits its execution environment.
[DATA_EXFILTRATION]: No sensitive file access or unauthorized network operations were found. While the skill permits web searching for research, it follows a defined policy and records sources in a structured JSON format.
[PROMPT_INJECTION]: The instructions are purely functional and do not attempt to override the AI's safety guidelines or core personality.
[REMOTE_CODE_EXECUTION]: There are no remote dependencies, script downloads, or dynamic code execution patterns within the provided files.

acceptance-criteria