Security audit

master-debate

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed debate-format writing aid and does not show hidden execution, credential access, persistence, or data exfiltration behavior.

Before installing, note that this skill will use subagents to generate multi-round religious debate content and may read related local reference files for citations. Review outputs for theological neutrality and citation accuracy, but there is no evidence of hidden system access or persistence.

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

MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
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)

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 77% confidence
Finding: The top-level documentation says the skill's purpose is to present multiple perspectives without judging superiority. However, the example closing at L267 says '哪个让你少打妄想就走哪个', which moves from neutral presentation into prescriptive guidance about what the reader should do.
Content: No source excerpt is available for this finding.