Security audit

胡田-OPC导师-概念验证中心

Security checks for vulnerabilities and agentic risk

Overview

This is a non-executable concept-validation guidance skill with no hidden data access, persistence, or privileged actions.

Installers should expect this skill to activate for concept validation, feasibility assessment, TRL review, and similar business or technical evaluation requests. The only notable caveat is that a couple of broad Chinese trigger phrases may make it activate more often than intended, but the skill itself does not execute code or access private data.

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 (1)

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The trigger list includes broad colloquial phrases such as “能不能做” and “行不行”, which are common in many unrelated user queries. This can cause the skill to activate outside its intended concept-validation context, leading to misrouting, confused task handling, and accidental exposure of this skill’s behavior when a more appropriate skill should respond.

Static analysis

No suspicious patterns detected.