Security audit

Quiz Battle

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Russian-language quiz skill with no code execution, persistence, credential handling, or hidden behavior.

Install this if you want a Russian-language Telegram-style quiz helper. Users who expect multilingual behavior or stricter activation should adjust the trigger language, but there is no evidence of malicious or high-impact hidden behavior.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Ae4

Medium

Category: analysis-evasion
Confidence: 80% confidence
Finding: Suspicious Unicode normalization or mixed-script content

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The skill description says to use the skill whenever the user asks to play a quiz or test knowledge across broad school subjects, which creates an overly generic trigger surface. This can cause accidental invocation in unrelated conversations, leading to context hijacking or unwanted tool-driven interaction when the user did not specifically request this skill.

Natural-Language Policy Violations

Medium

Confidence: 87% confidence
Finding: The skill content is entirely in Russian and instructs Russian-language behavior without any user language check or opt-in. This can override user preferences, degrade usability, and cause unsafe miscommunication if the broader conversation is in another language, especially when sending interactive prompts the user may not understand.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The usage instructions state 'Когда пользователь просит поиграть' ('when the user asks to play'), which is ambiguous because many non-quiz interactions can fit that phrase. In an agent environment, such ambiguity increases the chance of misrouting user intent and activating this skill in contexts where inline buttons or quiz flow are inappropriate.

Static analysis

No suspicious patterns detected.