ClawHub
Back to skill

Security audit

openshorts

Security checks across malware telemetry and agentic risk

Overview

This skill is coherent for video clipping, but it enables public social posting and third-party media processing without clear final consent checkpoints.

Review before installing. Use it only with videos you have rights to, avoid submitting private or internal URLs unless you trust the configured OpenShorts instance, and require your agent to ask for explicit approval of the exact clip, account/platforms, title, and schedule before any publish action.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Intent-Code Divergence

Medium
Confidence
95% confidence
Finding
The skill gives conflicting instructions for a rights-confirmation safeguard: the API example uses an `acknowledged` field while the rules say `confirm_rights` is required. This inconsistency can cause agents or users to omit the intended consent/rights check, leading to unauthorized processing of copyrighted content or failed enforcement of a legal/compliance control.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill enables publishing to TikTok, Instagram Reels, and YouTube Shorts but does not prominently require explicit user confirmation before account-impacting external actions. An agent following this skill could post content publicly or schedule posts on connected accounts without a clear consent checkpoint, creating reputational and operational risk.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill tells the agent to send video URLs and related clip-processing data to OpenShorts for remote processing, but it does not clearly warn that this transfers user content and metadata to an external service. This can expose private or sensitive media, internal URLs, or unpublished content to third-party processing without adequately informed consent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.