The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions and does not include any scripts, executables, or command execution patterns.
[SAFE]: No sensitive file access, network requests, or credential handling were identified in the instructions.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data (contract clause text provided by the user). While this creates an ingestion point for potential indirect prompt injection, the skill possesses no capabilities (such as file writing, shell access, or network communication) that could be used as an exploit vector. Consequently, the presence of this attack surface is considered safe.
[SAFE]: The skill maintains human-in-the-loop safety by explicitly stating it does not provide legal advice and suggesting specific questions for the user to ask qualified counsel.

clause-explainer