Security audit

Story Chain Multiverse

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only Chinese interactive story skill with optional adult story branches and no evidence of code execution, credential access, persistence, or data exfiltration.

Install this if you want a Traditional Chinese interactive fiction helper. Be aware it can suggest an adult branch, although the artifact says adult content should stay off unless the user explicitly enables it; users who do not want that should say to keep the story all-ages.

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 (6)

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The trigger phrases are broad enough to match ordinary conversation such as continuing a story, roleplay, or starting a new plot, which can cause the skill to activate unexpectedly outside a clearly scoped invocation. This increases the chance of prompt hijacking of unrelated user requests and may route users into a workflow that includes sensitive content paths such as fandom or R18 branches without strong upfront gating.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The response rules require every turn to be '180~350 字（中文）', which forces a specific language. There is no opt-in, fallback, or explanation that this is a region-specific skill, so the language constraint appears to violate the policy against unprompted locale/language forcing.

Natural-Language Policy Violations

Medium

Confidence: 88% confidence
Finding: The entire skill content is presented only in Traditional Chinese, with no indication that language selection is optional or that the skill is intended exclusively for a Chinese-speaking context. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.

Natural-Language Policy Violations

Medium

Confidence: 94% confidence
Finding: The entire skill content is written in Chinese and provides no indication that the user can choose another language or that the skill is intentionally limited to a Chinese-language audience for a documented reason. This matches the policy category for language or locale constraints imposed without user opt-in.

Natural-Language Policy Violations

Medium

Confidence: 96% confidence
Finding: This markdown file presents all user-facing content in a single language, which can amount to a language/locale policy violation when no user opt-in or alternative is provided. The content does not indicate that the skill is region-specific or that users may choose another language.

Natural-Language Policy Violations

Low

Confidence: 76% confidence
Finding: This markdown file includes distinct 'Chinese', 'English', 'Japanese', 'Korean', and 'Vietnamese' naming sections as prescriptive recommendations, but it does not explicitly frame them as optional choices based on user preference. Under the policy, language or locale constraints should be offered as a choice or clearly justified, and this section reads as a fixed locale taxonomy rather than an opt-in selection.

Static analysis

No suspicious patterns detected.