ClawHub

Editor Cinematic

Security checks across malware telemetry and agentic risk

Overview

This is a real cloud video-editing skill, but it can automatically create service sessions and send broad or ambiguous requests to a third-party backend, so users should review it before installing.

Install only if you are comfortable with a third-party video service receiving your editing prompts, uploaded footage, and session metadata. Use it with explicit commands, avoid confidential or regulated media, and confirm before allowing uploads, exports, credit checks, or ambiguous edit requests.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

Medium
Confidence
92% confidence
Finding
The manifest presents the skill as a simple video-editing tool, but the body instructs the agent to perform authentication, session creation, and credit/account-related API operations automatically. This expands the skill's effective capability beyond the declared purpose, which can mislead users and host platforms about what the skill will do with credentials and remote services.

Vague Triggers

Medium
Confidence
80% confidence
Finding
The invocation guidance is broad enough that ordinary conversation about editing or exporting could trigger the skill unexpectedly. Unintended activation matters more here because first interaction performs automatic setup against a remote API and may acquire tokens and create sessions without a clearly scoped user confirmation.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The catch-all rule routes 'Everything else' into the SSE editing path, creating an overly permissive trigger surface. In this skill, that can cause arbitrary user text to be forwarded to a backend editing service and initiate stateful remote actions even when the user did not clearly intend to invoke the skill.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal