Security audit

Cross Team Plain Language

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only rewriting skill for clearer cross-team communication, with no code execution, persistence, credential handling, or hidden data access.

Install this if you want help rewriting internal messages into clearer cross-team language. Be aware that its default format uses Chinese headings and examples, so explicitly ask for English or another language when needed.

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

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Natural-Language Policy Violations

Medium

Confidence: 91% confidence
Finding: The skill hard-codes a Chinese-language output structure and examples as the default behavior, which can override or bias the model away from the user's requested language. In cross-team communication workflows, this can cause incorrect-language responses, reduce usability, and create operational risk if users expect audience-appropriate English or multilingual output but receive Chinese by default.

Static analysis

No suspicious patterns detected.