Security audit

都市悬疑漫剧分镜生成器

Security checks for vulnerabilities and agentic risk

Overview

This skill creates storyboards and image prompts, with no evidence of hidden execution, sensitive access, or automatic publishing.

Only upload reference images you are authorized to share, since the selected image service will receive them. This skill provides plans and prompts; generating images and publishing videos are separate steps.

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

Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
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)

The workflow instructs uploading a character reference portrait to Jimeng without a privacy warning.

Medium

Category: Output Handling
Confidence: 97% confidence
Finding: This step explicitly instructs uploading a front-facing, half-body reference image to a third-party image-generation service. The file does not warn that the image will be shared with that service or advise obtaining permission when it depicts an identifiable person.
Content: No source excerpt is available for this finding.

The fixed output format requires Chinese Jimeng prompts and English Midjourney prompts without offering a language choice.

Low

Category: Output Handling
Confidence: 93% confidence
Finding: The skill explicitly prescribes the natural language of each generated prompt; this requirement is repeated at L67. It offers no language opt-in or override and does not explain why those languages are necessary for the respective tools.
Content: No source excerpt is available for this finding.

The skill mandates Chinese and English prompt outputs without user language opt-in.

Low

Category: Output Handling
Confidence: 97% confidence
Finding: The workflow requires a Chinese Jimeng prompt and an English Midjourney prompt for every shot, and the fixed output format repeats this requirement. These are explicit output-language requirements with no user choice or documented justification for why the tools require those languages.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.