The Agent Skills Directory

[SAFE]: The skill was analyzed for 11 threat categories, including prompt injection, data exfiltration, and remote code execution. No malicious patterns or security risks were identified. The content consists entirely of instructional text and checklists for corporate legal drafting.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest company documents (charters, bylaws, cap tables) provided by the user. While this creates a surface for indirect prompt injection, the skill possesses no exploitable capabilities such as file system writing, subprocess execution, or network exfiltration, rendering the risk safe in this context.

shareholder-agreement