ClawHub
Back to skill

Security audit

contentforge-api

Security checks across malware telemetry and agentic risk

Overview

This skill does what it claims, but users should understand it sends emails and content prompts to an external ContentForge/VCG API.

Install this only if you are comfortable using ContentForge/VCG as a third-party content generation provider. Before use, ask the agent to confirm before sending your email, prompts, product details, marketing plans, or other business content, and do not include secrets or sensitive personal data unless you have reviewed and accept the provider's 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 (3)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The invocation guidance is extremely broad, telling the agent to use this skill for essentially any content generation, blog writing, marketing copy, or text creation task. That can cause the agent to route ordinary writing requests to a third-party API by default, increasing unnecessary external data sharing and reducing user awareness and consent.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to collect the user's email address and send it to an external service to create an API key, but it does not provide a privacy notice, consent step, or explanation of how that personal data will be transmitted and used. This creates a privacy risk because personally identifiable information is shared off-platform without explicit warning or minimization.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The examples show sending user-supplied content inputs and an API key to a third-party generation API, but the skill never clearly warns that prompts, product details, marketing plans, or other potentially sensitive business content will leave the local environment. In practice, this can expose confidential or personal data to an external provider without informed user approval.

VirusTotal

VirusTotal findings are pending for this skill version.