Evez Debate Framework
PassAudited by ClawScan on May 12, 2026.
Overview
The skill appears to be a purpose-aligned multi-agent debate framework with no evidenced shell, network, credential, or persistence behavior, though its provenance is limited.
This looks safe to install as an instruction/code reference. If you extend it to call real LLMs, be mindful that debate topics and arguments may be sent to those providers, and verify the full script because the registry source provenance is limited.
Findings (1)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Users have less context for who maintains the code or where to verify updates, but the provided artifacts do not show unsafe behavior.
The skill includes a Python code file but has no public source or homepage listed, limiting independent provenance review. No suspicious install behavior or dependencies are evidenced.
Source: unknown Homepage: none
Review the included script before running or adapting it, especially if you plan to connect it to real LLM providers.