Security audit

Hybrid Dev

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed markdown-only development workflow guide and does not show hidden execution, credential access, persistence, or data exfiltration behavior.

Install this if you want a Chinese-language hybrid development workflow for planning, Copilot task handoff, and validation. Review the generated task packs before giving them to Copilot, especially because the skill is oriented around a specific customer registry MVP example and its triggers are broad enough that it may be selected for general iteration or validation requests.

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 (5)

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The description combines general use-cases and trigger phrases without clearly distinguishing advisory text from machine-consumable invocation conditions. This ambiguity can lead to over-selection of the skill and incorrect routing, especially because the skill governs a multi-phase development process that may influence planning, coding handoff, and validation behavior.

Vague Triggers

Medium

Confidence: 87% confidence
Finding: The description combines general use-cases and trigger phrases without clearly distinguishing advisory text from machine-consumable invocation conditions. This ambiguity can lead to over-selection of the skill and incorrect routing, especially because the skill governs a multi-phase development process that may influence planning, coding handoff, and validation behavior.

Natural-Language Policy Violations

Medium

Confidence: 90% confidence
Finding: The operational instructions and headings are written entirely in Chinese, which implicitly fixes the skill's interaction language without offering the user a language choice or documenting a justified locale restriction. This can violate language/locale policy when users are not explicitly opting into Chinese-only behavior.

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: The entire prompt suite is written as prescriptive Chinese-language instructions and does not provide any opt-in, alternative language, or explanation that the skill is limited to a Chinese-speaking or region-specific context. Under the policy, forcing a specific language without user choice is a natural-language policy violation.

Natural-Language Policy Violations

Low

Confidence: 94% confidence
Finding: This markdown file contains user-facing checklist instructions exclusively in Chinese, and there is no indication that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking context. Under the policy, forcing a specific language without opt-in is a natural-language policy violation.

Static analysis

No suspicious patterns detected.