ClawHub
Back to skill

Security audit

ContentStudio

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed ContentStudio automation helper, but it can affect real social media posts and should be used with explicit review before mutations.

Install this only if you trust the ContentStudio CLI and want your agent to manage your ContentStudio account. Treat create, approve, delete, upload, account-connect, and delete-from-social operations as high impact: review dry-run output, confirm the workspace and target posts/accounts, and avoid copying the README bulk scripts without adding a review step.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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 README explicitly states that after installation, the agent 'automatically knows when to use the contentstudio CLI without prompting.' For a skill that can create, approve, delete, and publish social-media content, broad auto-invocation increases the chance an agent will trigger high-impact actions without sufficiently explicit user confirmation or scoped intent checks.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The bulk-delete example loops through draft posts older than 30 days and deletes them with no safety interlock, dry-run step, confirmation gate, or warning about irreversible effects. In an agent context, cookbook-style destructive automation can be copied verbatim and cause mass unintended deletion of user content.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.