multi-brain-debate
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of Markdown templates and YAML configuration files that define a reasoning process. No patterns related to prompt injection, data exfiltration, or malicious behavior were detected.
- [NO_CODE]: The skill does not include any code, binary files, or external package dependencies. All logic is implemented via natural language instructions to the AI agent.
- [INDIRECT_PROMPT_INJECTION]: The skill provides a protocol for processing user input, which inherently carries an indirect prompt injection surface. However, the skill lacks any privileged capabilities that could be exploited.
- Ingestion points: Processes user-provided requests for high-stakes decisions through the debate workflow defined in
SKILL.md. - Boundary markers: Not explicitly defined in the templates.
- Capability inventory: None. The skill does not use tools for file manipulation, network access, or shell execution.
- Sanitization: None present.
Audit Metadata