Back to skill

Security audit

Seedance 2.0 Prompt-Optimizer Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-writing guide for Seedance 2.0 with no executable code, persistence, credential use, or hidden data access.

This skill appears safe to install as a Markdown prompt aid. Users should be aware it may activate for broad video-prompt requests, and should only apply culturally specific styles, language choices, watermark removal, or reference-asset uploads when they match the user's intent and rights to the material.

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
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 (5)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 165)May include surrounding context.

md
| `SKILL.md` | This file — master instructions |

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger conditions are broad enough to activate on generic requests like wanting to generate a video or describing a scene, even when the user may not specifically want Seedance 2.0. This can cause the agent to invoke the wrong skill, produce irrelevant instructions, or override a more appropriate workflow, reducing reliability and creating prompt-routing confusion.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The guidance states 'Write prompts in English for best international compatibility,' which imposes a specific language preference as a rule without user opt-in. Under the policy, forcing a language or locale without offering choice or documenting a justified regional constraint is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The document recommends the prompt phrase "2D Japanese anime style throughout," which imposes a specific language/locale-associated style choice in natural language guidance. There is no indication here that this is optional or user-selected, so it can conflict with a policy requiring user opt-in for language/locale-specific constraints.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The text recommends "3D Chinese fantasy CG style" as a natural-language prompt directive without clarifying that this should be selected only when the user wants that locale-associated style. This can be read as forcing a specific cultural/locale style absent explicit opt-in.

Content

No source excerpt is available for this finding.