The Agent Skills Directory

[NO_CODE] (SAFE): The skill consists entirely of Markdown documentation and templates. There are no Python scripts, Node.js files, or shell commands included in the package.
[DATA_EXPOSURE] (SAFE): The skill handles business-sensitive information (e.g., runway, traction, team details). It contains explicit safety instructions in SKILL.md to avoid requesting credentials or confidential customer/employee data, and it has no technical mechanism for exfiltrating this data.
[REMOTE_CODE_EXECUTION] (SAFE): No remote code execution patterns were detected. The skill does not perform any network requests or dynamic code evaluation.
[INDIRECT_PROMPT_INJECTION] (SAFE): Although the skill ingests user-provided company data, it possesses no exploitable capabilities (such as tool execution, file system writing, or network access), rendering indirect injection attempts inert.

fundraising