ClawHub
Back to skill

Security audit

supportforge-api

Security checks for vulnerabilities and agentic risk

Overview

This skill is coherent as a SupportForge API helper, but it can send sensitive customer-support data to a third-party service without clear consent or scoping guidance.

Review before installing. Use this only when you intentionally want SupportForge to process support data, and avoid sending customer PII, account values, interaction history, regulated data, or confidential business details unless you have approval and appropriate data-handling terms in place.

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
  • 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 (3)

Missing User Warnings

High
Confidence
98% confidence
Finding
The skill repeatedly instructs sending customer emails, ticket contents, sentiment data, account value, interaction history, and other potentially sensitive customer-support information to external API endpoints, but does not present a clear privacy warning or consent checkpoint first. In this context, the danger is elevated because support workflows commonly include PII, account data, complaint history, and commercially sensitive business information.

External Transmission

Medium
Category
Data Exfiltration
Content
### Step 2: Sign Up via API
```bash
curl -X POST https://supportforge.vosscg.com/v1/keys \
  -H "Content-Type: application/json" \
  -d '{"email":"user@example.com"}'
```
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The invocation guidance is overly broad: it triggers on generic customer-support-related requests without narrowing scope or requiring explicit user intent to use an external third-party service. In an agent environment, this can cause the skill to be invoked for ordinary support conversations and steer user/customer data into SupportForge unnecessarily.

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