ClawHub
Back to skill

Security audit

Webhook Http Request

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only AgentPMT HTTP request skill whose broad outbound request and authentication features are disclosed and match its stated purpose.

Install only if you intend to let your agent make outbound HTTP calls through AgentPMT. Treat URLs, headers, request bodies, bearer tokens, API keys, and passwords as sensitive: send them only to trusted HTTPS services, keep allow_private disabled unless you have a specific need, and avoid broad or accidental use when a prompt merely mentions a URL or request.

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 (6)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The activation keywords include very generic terms such as "request" and "url", which are likely to match many normal user prompts unrelated to this skill. That increases the chance of accidental invocation of a tool capable of sending arbitrary outbound HTTP requests, potentially causing unintended data transmission to external services.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
This skill can send headers, tokens, usernames, passwords, and request bodies to arbitrary external endpoints, but the description does not prominently warn users about that capability. Without a clear upfront warning, users or orchestrating agents may provide sensitive data without understanding it will leave the system boundary.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
This schema exposes powerful request capabilities, including arbitrary URLs, custom headers, bearer/basic authentication, and request bodies, but provides no explicit warning that user data and secrets may be transmitted to third-party endpoints. In an agent setting, that omission increases the risk of unsafe use such as sending sensitive data to untrusted services, misusing credentials, or enabling SSRF-like behavior when paired with permissive URL handling.

External Transmission

Medium
Category
Data Exfiltration
Content
{
  "action": "request",
  "request_method": "GET",
  "url": "https://api.example.com/protected/resource",
  "auth_type": "bearer",
  "auth_token": "eyJhbGciOiJIUzI1NiIs..."
}
Confidence
81% confidence
Finding
https://api.example.com/

External Transmission

Medium
Category
Data Exfiltration
Content
{
  "action": "request",
  "request_method": "GET",
  "url": "https://api.example.com/account",
  "auth_type": "basic",
  "auth_username": "myuser",
  "auth_password": "mypassword"
Confidence
84% confidence
Finding
https://api.example.com/

External Transmission

Medium
Category
Data Exfiltration
Content
{
  "action": "request",
  "request_method": "GET",
  "url": "https://api.example.com/v2/search",
  "auth_type": "header",
  "auth_header_name": "X-API-Key",
  "auth_header_value": "abc123def456"
Confidence
83% confidence
Finding
https://api.example.com/

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal