ClawHub
Back to skill

Security audit

Markdown Publish & Share

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says: it publishes markdown to a disclosed AutEng endpoint and returns a shareable link, with no evidence of hidden execution or unrelated access.

Install only if you want an agent to publish markdown through AutEng and create shareable links. Do not use it for secrets, private architecture notes, customer data, or internal documents unless they are approved for external sharing, and set an expiration time when temporary access is intended.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly instructs the agent to send user-provided markdown to a third-party remote service and return a public share link, but it provides no privacy warning, consent requirement, or guidance about sensitive data. This is dangerous because users may include internal documentation, credentials, architecture details, or other confidential material that would be externally transmitted and potentially made accessible via a shareable URL.

External Transmission

Medium
Category
Data Exfiltration
Content
description: Publish markdown and return share links using curl. Support markdown with mermaid diagrams such as component diagrams, flowcharts, and sequence diagrams. Also supports KaTex and code blocks. AutEng will return a shareable link to the published rendered document. Use cases include Software Architecture diagrams and documentation, Maths and Physics derivations and Systems documentation.
---

# AutEng Docs Curl Publish

Use this endpoint:
Confidence
92% confidence
Finding
This skill is designed around posting content to https://auteng.ai/api/tools/docs/publish-markdown/, which is an external transmission of user data. In context, external transmission is the core feature, but it still constitutes a security/privacy risk because the skill normalizes uploading potentially sensitive markdown without any trust boundary explanation or user approval flow.

External Transmission

Medium
Category
Data Exfiltration
Content
Extract a compact success payload:

```bash
curl -sS -X POST "https://auteng.ai/api/tools/docs/publish-markdown/" \
  -H "Content-Type: application/json" \
  -d '{"markdown":"# Hello\n\nPublished from curl."}' \
  | jq '{title, share_url, expires_at}'
Confidence
90% confidence
Finding
The example command again demonstrates sending markdown directly to a remote publishing endpoint and extracting a share_url, reinforcing a workflow that creates externally accessible artifacts. The danger is increased by the convenience of the example: it encourages easy publication while omitting warnings about confidential information, unintended disclosure, or the implications of generating a shareable link.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.