Safety Executor

PassAudited by ClawScan on May 1, 2026.

Overview

This is an instruction-only safety skill with no code or permissions, but its actual safety rules appear empty and should not be relied on as a complete command-safety policy.

This skill appears safe to install from a permissions standpoint because it has no code, install steps, credentials, or system access. However, its safety-rule sections are empty, so treat it as incomplete documentation rather than a reliable guardrail for executing system commands.

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.

Low

#ASI09: Human-Agent Trust Exploitation

What this means

A user or agent may assume the skill provides concrete command-safety restrictions when it actually contains little actionable policy.

Why it was flagged

The skill presents itself as a command-safety guide, but the sections that should contain the core blocking principles and controlled operations are empty placeholders.

Skill content

## 核心原则 
<HIGH_RISK_PRINCIPLES></HIGH_RISK_PRINCIPLES>

## 限制原则需要用户确认
<CONTROLLED_OPERATIONS></CONTROLLED_OPERATIONS>

Recommendation

Do not rely on this skill as a complete safety control unless explicit allowed, restricted, and blocked command categories are added.