ClawHub
Back to skill

Security audit

Seedance AI Video Gen

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently helps generate Seedance videos through the Volcengine Ark API, with expected API-key, network, media-sharing, and local-output risks but no hidden or destructive behavior found.

Install only if you intend to use Volcengine Ark/Seedance for video generation. Use a scoped or quota-limited ARK_API_KEY, leave ARK_API_URL at the trusted provider endpoint unless you know why you are changing it, and avoid sensitive prompts or private media unless you accept sending them to the provider and saving generated outputs locally.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (5)

Tainted flow: 'req' from os.environ.get (line 59, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Content
method="POST",
    )

    with urllib.request.urlopen(req) as resp:
        result = json.loads(resp.read().decode("utf-8"))
    return result
Confidence
94% confidence
Finding
The request destination is derived from the ARK_API_URL environment variable and then used directly in urllib.request.urlopen with an Authorization bearer token header. If an attacker can influence the environment or deployment configuration, they can redirect the request to an arbitrary host and capture the API key, making this a real SSRF/credential-exfiltration risk rather than a harmless configuration read.

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill instructs use of network access and environment variables such as ARK_API_KEY, but the metadata does not declare corresponding permissions. This creates a transparency and governance gap: users and the hosting platform may not realize the skill can exfiltrate data over the network or consume secrets from the environment.

Vague Triggers

Medium
Confidence
83% confidence
Finding
The description uses very broad trigger phrases like generic requests to 'make a video,' which can cause the skill to activate in many ordinary conversations. Overbroad invocation increases the chance of unintended execution, surprise network calls, API usage, and file creation without clear user intent.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The instructions say to download generated video files into the working directory and present them to the user, but they do not require prior notice or consent about local file creation. This can lead to unexpected disk writes, persistence of potentially sensitive media, and confusion about where files are stored.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill tells users that image, video, and audio URLs must be publicly accessible, but it does not warn that uploading personal media to public URLs may expose sensitive content to anyone with the link or via indexing/misconfiguration. In a multimodal media workflow, this materially raises privacy and data leakage risk.

Static analysis

No suspicious patterns detected.