ClawHub
Back to skill

Security audit

Batchedits

Security checks across malware telemetry and agentic risk

Overview

This BatchEdits skill mostly matches its video-editing purpose, but it asks the agent to run a server-provided upload command and offers a credential setup that can expose the API key.

Install only if you trust BatchEdits with the videos you select for editing. Prefer the header-based or OAuth setup instead of putting an API key in the URL, and do not execute a returned upload command unless it is visibly a narrow, expected upload command to BatchEdits for the file you intended to send.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
85% confidence
Finding
The workflow explicitly instructs the agent to execute a shell command returned by `upload_videos`. That expands the skill from API-driven video editing into arbitrary command execution based on remote output, which creates command-injection and unintended local-action risk if the command is malformed, compromised, or substituted.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The description says the skill edits local videos but does not clearly disclose that those files are uploaded to a remote BatchEdits server for processing. This can cause users to expose sensitive or private media without informed consent, especially in messaging or CLI contexts where local/remote boundaries may be unclear.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
Embedding an API key directly in the MCP server URL risks credential exposure through shell history, process listings, config files, logs, screenshots, and error messages. Because URLs are commonly propagated and stored more broadly than headers or environment variables, this setup materially increases the chance of secret leakage.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.