Back to skill

Security audit

seedance-video

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward SkillBoss video-generation helper that sends prompts and optional image URLs to SkillBoss as part of its stated purpose.

Install only if you are comfortable sending video prompts, generation settings, and any reference image URLs to SkillBoss under its billing and data-handling terms. Avoid using confidential prompts or private/internal image URLs unless you intend SkillBoss to process them.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill explicitly routes user prompts and potentially reference images to the external SkillBoss API, but the description and usage guidance do not clearly warn users that their content will leave the local agent environment for third-party processing. This creates a privacy and data-handling transparency issue, especially if users provide sensitive prompts, proprietary images, or regulated content under the assumption processing is local.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
84% confidence
Finding

This example shows outbound transmission of user-supplied prompts to https://api.skillboss.co/v1/run, which is expected for the skill’s function but still constitutes data exfiltration to an external service. The risk is not the existence of the API call itself, but the lack of safeguards or warnings around sending potentially sensitive user content and metadata to a third party.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

Text to Video

bash
curl -X POST "https://api.skillboss.co/v1/run" \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

External Transmission

Medium
Category
Data Exfiltration
Confidence
84% confidence
Finding

This example shows outbound transmission of user-supplied prompts to https://api.skillboss.co/v1/run, which is expected for the skill’s function but still constitutes data exfiltration to an external service. The risk is not the existence of the API call itself, but the lack of safeguards or warnings around sending potentially sensitive user content and metadata to a third party.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

Text to Video

bash
curl -X POST "https://api.skillboss.co/v1/run" \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 75)May include surrounding context.

Vertical Social Clip

bash
curl -X POST "https://api.skillboss.co/v1/run" \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

External Transmission

Medium
Category
Data Exfiltration
Confidence
92% confidence
Finding

This example sends reference image URLs along with prompts to the external SkillBoss API, which can expose sensitive visual data, proprietary assets, or internal URLs to a third party. Because image-guided generation may involve more sensitive content than plain text prompts, the lack of explicit warning and handling guidance makes this more dangerous in context.

Content

Scanner excerpt · SKILL.md (reported line 91)May include surrounding context.

Image-Guided Video

bash
curl -X POST "https://api.skillboss.co/v1/run" \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{