Security audit

Safety Executor

Security checks for vulnerabilities and agentic risk

Overview

This skill is only a small instruction file, but it claims to provide command-execution safety while leaving the actual safety rules empty.

Review before installing. This does not appear to contain malicious code, but it should not be relied on as a shell-command safety guard until the high-risk actions, confirmation requirements, and blocked command categories are explicitly defined.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The trigger condition '当需要执行系统命令时候' is extremely broad and can cause the skill to activate for nearly any command-related request. In a safety-oriented skill, this ambiguity is dangerous because the skill may be invoked without clear scoping, while its actual safety controls are empty placeholders, creating a false sense of protection around risky command execution.

Missing User Warnings

Medium

Confidence: 98% confidence
Finding: The skill claims to enforce 'core principles' and 'confirmation-required' controls, but both sections are empty tags. In the context of system command execution, missing warnings and missing concrete restrictions are dangerous because they can allow destructive, privilege-altering, or data-loss commands to proceed without any documented guardrails.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The usage section repeats the same vague instruction to 'always follow the core principles listed above,' but the referenced principles are not actually defined. This can mislead downstream agents or users into believing meaningful command safety checks exist when the document provides no enforceable restrictions.

Natural-Language Policy Violations

Low

Confidence: 84% confidence
Finding: Key descriptive and instructional text is presented in Chinese, while other sections are in English, and the file does not state that the skill is intended only for Chinese-speaking users or offer a language choice. This creates a potential language/locale policy issue because the skill may impose a language preference without explicit user opt-in.

Static analysis

No suspicious patterns detected.