The Agent Skills Directory

[NO_CODE]: The skill consists entirely of markdown instructions and does not include any executable scripts, shell commands, or external dependencies.
[SAFE]: No security threats were identified across the analyzed categories. The skill focuses on analyzing text provided by the user and provides a structured output format without requesting access to sensitive system resources, credentials, or the network.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data (employment contracts). While this presents an ingestion surface, the skill lacks access to exploitable capabilities such as shell execution, network operations, or file system writes. The risk is limited to potential output poisoning or instructional confusion within the chat session.

employment-contract