Security audit

Tech Debate

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only skill that structures technical debates and does not request file access, commands, credentials, network use, or persistence.

Install this if you want a structured debate assistant for technical decisions. Be aware that it is primarily Chinese-language and may activate on broad debate phrasing; avoid entering sensitive proprietary topics unless you are comfortable having them used in the current agent session.

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: 83% confidence
Finding: The trigger examples include very generic everyday phrases such as "tech debate" and broad natural-language variants, which can cause the skill to activate when the user did not explicitly intend to enter a multi-agent debate workflow. Unintended activation can disrupt normal assistant behavior, pull the conversation into a structured role-play flow, and create prompt-routing confusion that may be abused to derail user sessions.

Natural-Language Policy Violations

Medium

Confidence: 75% confidence
Finding: The skill description and interaction examples are Chinese-only and do not indicate that the skill will adapt to the user's language, which can force or strongly bias interaction into a language the user did not choose. This is primarily a safety and usability issue: users may misunderstand the workflow, intervention options, or outputs, leading to incorrect operation or reduced transparency.

Static analysis

No suspicious patterns detected.