marisa-rapid-prototyping
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides a methodological framework for software experimentation and decision-making without including executable code, scripts, or package dependencies.
- [SAFE]: The instructions incorporate defensive safety practices, explicitly directing the agent to only run experiments when "safe and authorized" and to establish sandbox boundaries and cleanup procedures.
- [SAFE]: The skill includes a reference to the author's repository on GitHub for provenance information, which is a legitimate vendor resource used for documentation purposes.
- [SAFE]: No prompt injection, obfuscation, or persistence mechanisms were detected in the skill instructions or supporting files.
Audit Metadata