ClawHub
Back to skill

Security audit

Social Content Generator

Security checks across malware telemetry and agentic risk

Overview

This appears to be a normal social media content generator, with the main caution that AI mode sends prompts to OpenAI and optional publishing credentials need careful handling.

Install only if you are comfortable with post topics and image prompts being sent to OpenAI when AI mode is used. Use --no-ai for local template-only generation, avoid entering confidential campaign or client information, keep .env files and API tokens out of source control, and do not provide social-platform tokens or run any upload workflow unless you separately review the uploader code.

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 (4)

Vague Triggers

Medium
Confidence
77% confidence
Finding
The skill's description and 'use when' scope are broad enough to match many ordinary marketing or content-generation requests, increasing the chance of over-triggering. In practice, that can route users into a workflow with file generation, image generation, and possible external API use even when they only wanted simple drafting help.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The README explicitly mentions uploading posts to social platforms via API credentials but does not clearly warn that prompts, generated content, metadata, or media may be transmitted to third-party services. In a social publishing context this is especially relevant because content may be auto-posted publicly or sent to external providers, creating confidentiality, privacy, and reputational risks if users are not warned first.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The script sends user-supplied topic text to OpenAI for generation, but its CLI description and help text do not clearly warn that input will be transmitted to a third-party service. In a content-generation skill, users may reasonably paste sensitive campaign plans, unreleased product names, or client information, so the lack of explicit disclosure creates a real privacy and data-handling risk even though it is not an exploit in the traditional code-execution sense.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
When image generation is enabled, the script sends prompts to OpenAI, retrieves a remote image URL, downloads the returned content, and writes it to disk without a prominent warning that remote transmission and local file creation will occur. In this skill context, that is more concerning because users may run it in automation pipelines or trusted workspaces and may not expect externally generated files to be fetched and saved automatically.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.