ClawHub

Video Cog

Security checks across malware telemetry and agentic risk

Overview

This is a coherent CellCog video-generation skill, with no bundled executable code or hidden behavior, but users should treat it as a paid external service that receives their prompts and media inputs.

Install only if you trust CellCog and are comfortable using a CellCog API key. Avoid sending secrets, confidential business material, regulated personal data, or real people’s likeness/voice unless you have approval and understand CellCog’s terms, retention, billing, and synthetic-media policies.

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 (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The skill description and examples are very broad and encourage use across many video-generation scenarios without defining clear trigger boundaries, exclusions, or negative examples. In an agent ecosystem, this can cause over-invocation or inappropriate invocation for requests involving sensitive, copyrighted, deceptive, or privacy-impacting media generation, increasing the chance that user data or unsafe content is sent to a third-party service unnecessarily.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill requires an API key and performs remote processing, but it does not prominently warn that prompts, scripts, and possibly media inputs will be transmitted to an external service. Users or higher-level agents may therefore supply confidential, personal, or regulated data without informed consent, creating privacy, compliance, and data-governance risk.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal