Security audit

seedance-combat-prompt

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language prompt-writing skill for Seedance anime fight videos, with no executable code, credential handling, persistence, or hidden data access.

Install this if you want a Chinese-language Seedance combat-prompt generator. Expect stylized fictional fight and impact descriptions, and note that some advanced weapon reference files mentioned by the skill are absent from the submitted package.

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
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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)

Natural-Language Policy Violations

Medium

Confidence: 89% confidence
Finding: The entire skill description is written only in Chinese and presents the agent as a Chinese prompt generator, but nowhere offers an opt-in language choice or states that outputs may be produced in other languages. Under the language/locale policy, a skill should not implicitly force a specific language unless the constraint is clearly documented and justified.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The README says to trigger the skill in conversation with the phrase "生成一条 seedance 二次元打戏提示词", but it does not define whether this is the only trigger, what variants are supported, or when the skill should not activate. For a markdown skill description, this leaves activation conditions ambiguous and risks unintended invocation from similar everyday requests about generating prompts.

Natural-Language Policy Violations

Medium

Confidence: 97% confidence
Finding: The description and core instruction text are entirely in Chinese and define the agent identity and task in Chinese only, with no indication that users may choose another language. This creates a language-policy issue because the skill effectively fixes a specific language/locale without user opt-in or a documented region-specific justification.

Static analysis

No suspicious patterns detected.