MOA-Debate
ReviewAudited by ClawScan on May 10, 2026.
Overview
Prompt-injection indicators were detected in the submitted artifacts (system-prompt-override); human review is required before treating this skill as clean.
This looks safe to install as an instruction-only debate helper. Be aware that it may make many model calls during a full debate and can produce persuasive arguments on both sides of a motion. ClawScan detected prompt-injection indicators (system-prompt-override), so this skill requires review even though the model response was benign.
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.
The assistant will adopt persuasive debate personas during the requested debate, but the artifacts do not show unrelated control, tool use, or data access.
The artifact contains prompt-like role instructions, which can resemble prompt-injection patterns, but here they are explicitly part of the debate simulation and are limited to generated debate turns.
Use this system prompt: > You are a skilled Oxford Union debater arguing FOR the proposition...
Use it when you want a structured debate simulation, and treat generated arguments as rhetorical outputs rather than verified facts.