Security audit

bible-skill

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language Bible study skill made of Markdown guidance and templates, with no code, credential access, persistence, or hidden data flows.

Install this if you want Chinese-first Bible study, sermon, devotional, or theology assistance. Ask for your preferred language, Bible translation, or denominational perspective when needed, and review theological outputs as study aids rather than authoritative pastoral advice.

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
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Natural-Language Policy Violations

Medium

Confidence: 86% confidence
Finding: This markdown file contains user-facing natural language exclusively in Chinese, beginning with the title and continuing throughout the document. Under the policy, forcing a specific language without user opt-in can be a locale/language policy violation when no alternative language choice or justification is provided.

Natural-Language Policy Violations

Medium

Confidence: 94% confidence
Finding: The skill is explicitly framed and written as a Chinese output template, which can steer the agent to answer in Chinese even when the user did not request that language. This is a policy/quality vulnerability because it can override user preference, reduce usability, and create prompt-priority conflicts, though it does not directly enable code execution or data exfiltration.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The instruction to automatically choose the most suitable template based on the user's question is overly broad and lacks scope controls, which can cause the skill to activate for loosely related prompts and dominate normal assistant behavior. In prompt-injection terms, this increases the chance of unintended instruction capture, format lock-in, and user-intent misinterpretation across a wide range of religious or textual questions.

Natural-Language Policy Violations

Low

Confidence: 91% confidence
Finding: This README consistently instructs use of the skill in Chinese and provides all example prompts and user guidance only in Chinese. Under the language/locale policy rule, forcing a specific language without offering user choice or documenting a justified locale constraint can be a policy violation.

Natural-Language Policy Violations

Low

Confidence: 82% confidence
Finding: The instruction says to '优先使用中文和合本（CUV）作为默认译本', which imposes a Chinese default on responses and source usage. Under the policy, forcing a specific language or locale without user opt-in can be a natural-language policy violation unless a justified regional constraint is documented.

Static analysis

No suspicious patterns detected.