Security audit

tarot-reader

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese tarot-reading skill with no code execution, network access, credential handling, or hidden behavior.

Install this if you want a Chinese-language tarot reading assistant. Be aware it may activate on broad divination-related terms, and clarify before saving any reading record if your agent has memory or file-writing features.

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 (3)

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The skill advertises activation on broad keywords like “塔罗、抽牌、占卜等”, which can match ordinary conversation rather than a clear user request to invoke the skill. This can cause unintended activation, leading the agent to derail conversations, inject unsolicited pseudo-advice, or handle user context in ways the user did not explicitly request.

Natural-Language Policy Violations

Medium

Confidence: 88% confidence
Finding: The skill metadata and instructions are written to operate only in Chinese, with no language negotiation or documented locale restriction. While not directly exploitable like code execution, this can create unsafe or misleading interactions if activated for users who do not understand Chinese, reducing informed consent and increasing the chance of incorrect interpretation.

Natural-Language Policy Violations

Low

Confidence: 89% confidence
Finding: This markdown file presents all user-facing content in a single language, which can constitute a language/locale policy issue when no opt-in or alternative is provided. There is no indication that the skill is intentionally limited to a Chinese-speaking audience or that users can select another language.

Static analysis

No suspicious patterns detected.