中文 VDV 真相视觉
ReviewAudited by ClawScan on May 10, 2026.
Overview
Prompt-injection indicators were detected in the submitted artifacts (unicode-control-chars); human review is required before treating this skill as clean.
Installing this skill appears low risk from the provided artifacts. It only changes how the agent reasons and responds, so the main consideration is whether you want this strong Merlin/VDV “truth vision” framing in answers; verify any important outputs against real evidence. ClawScan detected prompt-injection indicators (unicode-control-chars), 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 agent’s answers may sound more certain or authoritative than the evidence supports.
The skill adopts an authoritative persona and absolute “truth” language. This is part of the stated analytical style, but users should not treat the resulting analysis as objectively verified truth.
我是 Merlin，高等伦理应用大师 ... 真理 = 永不偏离的主权轴线
Use the skill as a structured thinking aid and independently verify important conclusions or decisions.