new-case
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is document organization and metadata extraction for legal professionals. Analysis of the instructions and templates revealed no evidence of obfuscation, malicious intent, or unauthorized data exfiltration.
- [COMMAND_EXECUTION]: The skill specifies the use of the
dateshell command to retrieve current timestamps for legal document creation and deadline tracking. This is a standard utility function and is used within the context of the skill's legitimate administrative duties. - [PROMPT_INJECTION]: The skill processes external, user-provided documents to extract case details. While this provides a surface for indirect prompt injection if the source materials contain adversarial text, no malicious instructions are present within the skill's own prompts.
Audit Metadata