Security audit

故事音乐技能

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Chinese-language story and music helper with disclosed save, export, and sharing examples, but users should review content before storing or sharing it.

Installers should treat this as a benign story/music helper. Before using export or sharing features, review the generated story for names, child-related details, private preferences, or copyrighted material, and choose safe output locations and sharing destinations deliberately.

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Missing User Warnings

High

Confidence: 96% confidence
Finding: The skill describes generating share links and posting stories to external platforms without any privacy notice, consent requirement, or data-sharing warning. Because this skill is designed for story creation and may include children's names, personal preferences, or other sensitive content, silent or poorly explained sharing can expose private data to third parties or broader audiences than intended.

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: The description and heading present the skill in a single enforced language, and the document does not indicate that users may choose another language or that the skill is intentionally limited to a Chinese-speaking context. This can violate language/locale policy when a skill imposes a locale without explicit opt-in or justification.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The skill explicitly documents exporting generated stories to text, audio, and video files without warning that user-provided or model-generated content will be written to disk. In practice, this can lead to unintended local persistence of sensitive prompts, names, children's stories, or copyrighted content, especially in a storytelling skill that may process personal or private material.

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: This code file contains pervasive Chinese-only titles, prompts, and instructions in the docstring and printed output. Under the policy criteria, forcing a specific language without user opt-in is a natural-language policy violation when no locale choice or justification is provided.

Context-Inappropriate Capability

Low

Confidence: 90% confidence
Finding: The skill's stated purpose is generating stories, selecting music, controlling playback, and adding narration. Injecting a hard-coded local filesystem path into sys.path is a development/environment manipulation capability, not a direct or obvious requirement of that purpose.

Static analysis

No suspicious patterns detected.