Security audit

AI KEY·做成一个技能

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local workflow-to-skill helper with disclosed file and memory use, and its risks are mostly about accidental activation rather than hidden or malicious behavior.

Install this only if you want an agent to create local reusable skills from completed work. Review the generated skill and memory entry before relying on them, and use explicit slash commands if you want to avoid accidental activation from casual wording.

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

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

Findings (2)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The English trigger phrases such as "make this a skill" and "save this workflow" are broad enough to match ordinary conversation, which can cause unintended invocation of this skill. In this skill's context, accidental activation is more concerning because it may steer the agent into creating or modifying reusable skills and related memory artifacts when the user only meant to speak descriptively.

Natural-Language Policy Violations

Low

Confidence: 81% confidence
Finding: The natural-language description hard-codes both Chinese and English invocation language, but does not state whether the user can choose their preferred language or locale. This can violate language-choice policy when a skill implicitly assumes or imposes language behavior without opt-in.

Static analysis

No suspicious patterns detected.