ClawHub

Dola Seedream

Security checks across malware telemetry and agentic risk

Overview

This appears to be a normal BytePlus Seedream image-generation skill; the main thing to understand is that prompts and reference images are sent to BytePlus for processing.

Install only if you intend to use BytePlus Seedream and are comfortable sending prompts and any reference images to BytePlus. Use a limited API key, avoid sensitive or confidential prompts/images, and verify ARK_DOLA_API_BASE is not overridden to an endpoint you do not trust.

SkillSpector

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

Vague Triggers

Medium
Confidence
87% confidence
Finding
The invocation description is broad enough to match many ordinary image-generation requests, which can cause over-triggering of the skill. In context, that matters because the skill performs external API calls and may transmit user prompts and reference images to a third party, so accidental activation can become an unintended data-sharing event.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The 'When to Use This Skill' section uses broad, high-level criteria without scope limits, making unintended invocation more likely. Because this skill can send prompts and reference image inputs over the network to an external provider, ambiguous activation increases the chance of unnecessary external disclosure or policy bypass through over-selection.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The documentation does not clearly warn that reference image URLs or Base64 image data may be transmitted to an external service. In an image-to-image skill, this omission is significant because users may supply sensitive or proprietary images, and silent off-platform transfer creates privacy, confidentiality, and compliance risks.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The script transmits user prompts and optional reference image URLs to a third-party BytePlus API, which can expose sensitive user data or internal resource locations without any explicit in-code warning, consent flow, or validation. In an agent-skill context, users may not realize their content is leaving the local environment, and reference URLs could include private or internal resources whose disclosure increases privacy and data-handling risk.

VirusTotal

No VirusTotal findings

View on VirusTotal