nda-review-jamie-tso
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed exclusively of instructional Markdown documentation and a standard license file. No executable scripts, binary files, or configuration files that trigger command execution were found.
- [REMOTE_CODE_EXECUTION]: No patterns of remote script downloading or execution were detected. The skill does not install packages or run external commands.
- [DATA_EXFILTRATION]: No network operations or file system write commands were found. The skill requests deal-specific context to perform its analysis, but this data remains within the session context with no mechanism for external transmission.
- [PROMPT_INJECTION]: The instructions provide a structured framework for legal review and do not attempt to override the underlying agent's safety protocols or system instructions.
- [INDIRECT_PROMPT_INJECTION]: The skill is intended to ingest and analyze untrusted external text (NDA documents). While this represents a theoretical injection surface, the skill has no associated capabilities—such as network access or shell execution—that could be leveraged for an attack.
Audit Metadata