ClawHub
Back to skill

Security audit

Auteng Docs Curl Publish

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: it publishes markdown to AutEng and returns a shareable link, with no hidden persistence or local privilege behavior found.

Install only if you are comfortable sending the markdown you choose to publish to AutEng and receiving a shareable URL. Do not use it for secrets, credentials, private customer data, or internal documents unless you understand AutEng's access, retention, and expiration behavior.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly instructs sending user-provided markdown to a third-party remote service and returning a shareable URL, but it provides no warning that the content leaves the local environment and may become accessible via that link. This creates a real risk of unintended disclosure of sensitive data, especially because users may assume the action is a local formatting or rendering step rather than publication.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
96% confidence
Finding

This skill directs the agent to POST arbitrary markdown to an external endpoint, which is an external data transmission action. In context, the transmission is the core feature, but it is still security-relevant because the content may include secrets, internal notes, credentials, or proprietary diagrams that would be exfiltrated to a remote service.

Content

Scanner excerpt · SKILL.md (reported line 6)May include surrounding context.

md
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.
---

# AutEng Docs Curl Publish

Use this endpoint:

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 44)May include surrounding context.

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}'

Static analysis

No suspicious patterns detected.