Security audit

SeedDance AI Video Generation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward SeedDance API integration guide, with expected external API and SDK use but some privacy and package-verification cautions.

Before installing, verify that seeddance-sdk is the official SDK, pin a reviewed version, and keep SEEDDANCE_API_KEY scoped and out of source control. Treat prompts, uploaded images/videos, generated outputs, and webhook metadata as data sent to external services, and avoid submitting sensitive or regulated content unless that is approved for your use case.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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

Findings (1)

T08 · Insecure Dependencies

Error

Location: SKILL.md:21
Finding: Installation of an Unverified and Unpinned Third-Party SDK
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill instructs users to send prompts, images, and videos to a third-party API but does not disclose that this transfers potentially sensitive user content off-platform for external processing. In a media-generation context, prompts and uploaded media may contain personal, proprietary, or regulated data, so lack of notice can lead to privacy, compliance, and data-governance risks.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 86% confidence
Finding: The skill description and all instructional content are written exclusively in Chinese, with no indication that users may choose another language or that the skill is intentionally limited to a Chinese-only audience for compliance reasons. This can violate language or locale policy when a skill imposes a specific language without user opt-in.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The webhook example shows asynchronous task completion via a remote callback endpoint but does not warn that task identifiers, status, metadata, and possibly result URLs or payloads will be delivered to that endpoint. This can expose generated content or operational metadata to unintended recipients if users configure insecure, third-party, or misrouted webhook URLs.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: L024 说明安装完成后 SDK 会自动配置本地环境并验证兼容性，但后续 L028-L063 又要求用户手动创建 seeddance.config.json 并设置 API 密钥环境变量。这构成了文档意图层面的矛盾：自动配置的表述与实际所示操作流程不一致。
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.