ClawHub
Back to skill

Security audit

supportforge-api

Security checks across malware telemetry and agentic risk

Overview

This is a coherent SupportForge API helper, but it can send customer support data and an API key to a third-party service.

Install only if you intend to use SupportForge for customer-support automation. Verify the provider and domain, use a dedicated API key, avoid pasting real secrets into chats or logs, and do not send real customer emails, account identifiers, billing details, or ticket history unless you are authorized to share that data with SupportForge.

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 (2)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The skill’s invocation guidance is broad enough to activate on generic customer-support requests, which can cause the agent to route ordinary user conversations into this external-API workflow without clear user intent. In this skill’s context, that over-triggering is more dangerous because many examples transmit customer messages, emails, IDs, and account context to third-party endpoints.

Missing User Warnings

High
Confidence
98% confidence
Finding
The skill repeatedly instructs sending customer communications, email addresses, account identifiers, sentiment data, and support context to external SupportForge endpoints without a clear privacy notice, consent step, or data-minimization guidance. In a customer-support setting this is especially sensitive because support tickets often contain personal data, order details, billing issues, and potentially confidential business information.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:46