ClawHub
Back to skill

Security audit

doubao-seedance-skill

Security checks across malware telemetry and agentic risk

Overview

This skill coherently calls Volcengine Seedance to generate videos, using an API key and saving generated files locally as expected for its purpose.

Install only if you are comfortable sending prompts and reference images to Volcengine and using a Volcengine API key that may consume quota or incur charges. Keep the API key out of shared files and logs, review the output directory before use, and consider adding URL validation, timeouts, and size limits before relying on the auto-download behavior in sensitive environments.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Tainted flow: 'video_url' from requests.get (line 127, network input) → requests.get (network output)

Medium
Category
Data Flow
Content
filepath = os.path.join(output_dir, filename)
                
                print(f"正在下载视频...")
                video_response = requests.get(video_url)
                with open(filepath, "wb") as f:
                    f.write(video_response.content)
                local_paths.append(filepath)
Confidence
88% confidence
Finding
video_response = requests.get(video_url)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill requires network access and an API key from the environment, but it does not declare corresponding permissions. This creates a transparency and policy-enforcement gap: an agent may invoke external services and use sensitive credentials without explicit user-facing disclosure or platform-level review of those capabilities.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill says it will 'directly run' the API call and return a local file, but it does not clearly warn users that their prompt data will be sent to a third-party API and that generated videos will be written to local storage. This can lead to unintentional disclosure of sensitive prompts or unexpected local file creation, especially in environments where users assume processing is local.

Missing User Warnings

Low
Confidence
88% confidence
Finding
The metadata declares a required environment variable for an API key but provides no warning about handling secrets. This increases the risk of unsafe operational use, such as exposing the credential in logs, debugging output, screenshots, or misconfigured execution environments.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.