ClawHub
Back to skill

Security audit

markdown.new/crawl

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward helper for crawling public websites via markdown.new, with the main caveat that target URLs are sent to that external service.

Install this only if you are comfortable using markdown.new for crawl requests. Use it for public documentation or public site sections, keep limits and depth narrow, and do not provide private URLs, authenticated pages, localhost or internal hosts, secrets, or tokenized links.

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
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • 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
Findings (4)

Tool Parameter Abuse

High
Category
Tool Misuse
Content
- `POST /crawl`: create async crawl job and return job ID.
- `GET /crawl/status/{jobId}`: return crawl output and status.
- `DELETE /crawl/status/{jobId}`: cancel a running crawl; completed pages remain available.
- `GET /crawl/{url}`: browser-style shortcut that starts crawl and returns tracking page.

### Common Crawl Options
Confidence
80% confidence
Finding
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger description is broad enough to activate on many URL-extraction or documentation requests without clear boundaries on when external crawling should or should not be used. In practice, this can cause the agent to invoke a third-party crawl service for requests that may not require it, increasing the chance of unintended data disclosure or over-collection.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill instructs use of an external service but does not warn that requested URLs and crawl targets will be transmitted to a third party. This creates a privacy and data-handling risk because users may provide internal docs, pre-release URLs, or other sensitive targets without informed consent.

External Transmission

Medium
Category
Data Exfiltration
Content
### Core Commands

```sh
curl -X POST "https://markdown.new/crawl" \
  -H "Content-Type: application/json" \
  -d '{"url":"https://docs.example.com","limit":50}'
```
Confidence
95% confidence
Finding
This command sends a user-supplied target URL to an external service, which is a real data egress path even if the feature is intended. If the target contains sensitive internal locations, tokens in query strings, or confidential document endpoints, the skill could leak that information to the third party and trigger unauthorized crawling of private resources.

Static analysis

No suspicious patterns detected.