ClawHub

Ai Image To Video Com

Security checks across malware telemetry and agentic risk

Overview

This skill performs the advertised cloud image-to-video work, but it automatically creates external service sessions and can send broad user prompts or media to a third-party backend without a clear consent boundary.

Review before installing. Use it only if you are comfortable sending images, prompts, edits, and generated media to NemoVideo's cloud backend. Avoid private or sensitive media unless you understand the service's retention, download-link, token, credit, and deletion behavior.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
81% confidence
Finding
The skill instructs the agent to automatically obtain anonymous tokens and use a credit-bearing external account without explicit user consent or a clear trust boundary. That expands the skill from simple media processing into credential acquisition and resource consumption on a third-party service, which can cause unintended account creation, billing/credit use, and opaque data transfer to an external backend.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The catch-all route sends 'everything else' to the external SSE backend, which can cause unrelated or ambiguous user requests to be forwarded off-platform. In practice, this widens the trigger surface substantially and increases the chance of accidental data exfiltration, unexpected third-party processing, and misuse beyond the skill's advertised purpose.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly tells the agent to connect to an external API before handling user requests while keeping those technical details out of the chat. Hiding token handling and backend transmission deprives users of informed consent about where their files and prompts are going, making covert third-party data transfer more dangerous in a skill that processes user media.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal