ClawHub
Back to skill

Security audit

Content Draft Generator

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent content-drafting helper, but users should know it fetches provided URLs, may use FxTwitter for X/Twitter links, and saves local draft files.

Install only if you are comfortable with the agent fetching the URLs you provide and storing generated markdown files locally. Prefer public reference links; avoid private, internal, signed, or tokenized URLs, and review or delete generated files if they contain confidential positioning, strategy, or draft content.

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
92% confidence
Finding
The skill description is broad enough to activate on generic content-creation requests, which can cause unintended invocation of a workflow that fetches external URLs and persists multiple files. That increases the chance of surprising data handling and external access without the user clearly intending those actions.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The workflow instructs the agent to fetch external content and save several intermediate and final artifacts, but it does not require an upfront user warning or explicit consent for those actions. This creates a privacy and transparency risk because user-provided URLs, derived analyses, and generated drafts may be stored unexpectedly.

External Transmission

Medium
Category
Data Exfiltration
Content
### Step 2: Content Deconstruction

1. Fetch content from all reference URLs (use web_fetch tool)
2. For Twitter/X URLs, transform to FxTwitter API: `https://api.fxtwitter.com/username/status/123456`
3. Analyze each piece following the `references/content-deconstructor.md` guide
4. Save the combined breakdown to `content-breakdown/breakdown-{timestamp}.md`
5. Report: "✓ Content breakdown saved"
Confidence
95% confidence
Finding
The skill explicitly rewrites Twitter/X URLs to a third-party FxTwitter endpoint, causing user-requested content retrieval to be sent to an external service not clearly disclosed as a separate processor. This can expose requested URLs and access metadata to an additional domain and changes the trust boundary beyond the original source site.

External Transmission

Medium
Category
Data Exfiltration
Content
**Transform:**
- Input: `https://x.com/username/status/123456`
- API URL: `https://api.fxtwitter.com/username/status/123456`

## Error Handling
Confidence
95% confidence
Finding
The repeated URL transformation guidance reinforces use of a third-party API for Twitter/X content, again introducing undisclosed external transmission and dependency on a non-origin service. Because this is baked into the handling rules, the behavior is systematic rather than incidental, increasing the likelihood of unintended data sharing.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.