The Agent Skills Directory

[SAFE]: The skill is composed solely of markdown instructions and metadata. It does not include any executable scripts, software dependencies, or binary files.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze external documents (NDAs). While these documents are untrusted inputs that could theoretically contain adversarial instructions (indirect prompt injection), the skill definition does not include any tools or capabilities—such as network access, file system modification, or shell command execution—that could be exploited to cause technical harm. The risk is limited to the accuracy of the classification logic itself.

nda-screening