The Agent Skills Directory

[SAFE]: The skill contains no executable code or scripts, serving purely as a set of instructions for the agent's behavior during legal analysis.
[EXTERNAL_DOWNLOADS]: The instructions direct the agent to verify legal norms and case law using established, official databases such as gesetze-im-internet.de, dejure.org, and openJur. These references are standard for the intended legal research purpose and target well-known, trusted domains.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-supplied legal documents and case facts. However, it does not utilize any high-risk capabilities—such as command execution, arbitrary file writing, or network exfiltration—that could be exploited by malicious content within those documents. The risk of harmful outcomes from processing external data is negligible.
[PROMPT_INJECTION]: No patterns were found that attempt to override system safety guidelines, disable filters, or extract system prompts. The instructions are consistently focused on legal methodology and quality control.

dual-licensing