Security audit

Seedance Assistant

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language Seedance prompt-writing helper made of documentation and templates, with no executable code or privileged behavior.

Install this if you want a Chinese-language assistant for creating Seedance/Jimeng video prompts. Non-Chinese users may find it less accessible, and users should only provide media they have the right to use and upload to the Seedance platform.

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 (8)

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The activation description is broad enough to trigger on many generic video-creation requests, not just narrow Seedance-specific tasks. This can cause the skill to intercept unrelated user intents, override more appropriate skills or base behaviors, and increase the chance that its instructions dominate conversations unexpectedly.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The skill content is written to operate in Chinese and instructs the agent to ask questions and respond in that language without offering a user-language fallback. This can degrade reliability for non-Chinese users, create confusion, and make the skill effectively unusable or misleading when activated for users communicating in other languages.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: All instructional text and examples in this file are presented in Chinese, which can impose a language constraint on users or downstream agents without any stated opt-in. The policy requires either a user language choice or a clearly documented justification for restricting the skill to a specific language or locale.

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: This file’s natural-language instructions and examples are fully Chinese, and there is no indication that users can opt into another language or that the template is intended only for a Chinese-language workflow. Under the stated policy, forcing a specific language without user choice is a locale/language policy concern.

Vague Triggers

Low

Confidence: 77% confidence
Finding: This plain-text template describes how to imitate camera movement from a reference video, but it does not define any explicit activation boundaries, allowed trigger phrases, or negative examples. In a skill context, such broadly framed invocation language can make it unclear when the template should be used versus when a different prompt template is intended.

Natural-Language Policy Violations

Low

Confidence: 97% confidence
Finding: This plain-text skill file contains only Chinese instructions and examples, with no indication that the user can select another language or locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Natural-Language Policy Violations

Low

Confidence: 91% confidence
Finding: This plain-text skill file presents all instructions, templates, and examples exclusively in Chinese. Under the policy for natural-language violations, forcing a specific language without user opt-in can be a locale/language policy issue when no alternative or choice is provided.

Natural-Language Policy Violations

Low

Confidence: 97% confidence
Finding: This markdown file is natural-language documentation, and its title and all instructional content are presented only in Chinese. Under the policy-violation rule, forcing a specific language without user opt-in can be a locale policy issue when no alternative language option or justification is provided.