ClawHub
Back to skill

Security audit

QuorumAI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent QuorumAI API integration, but its documented curl examples unsafely substitute user text into shell commands and could let crafted prompts run local commands.

Review before installing. Use this only for questions you are willing to send to QuorumAI and potentially expose through a public result link. The skill should be updated to build JSON with a safe serializer or structured HTTP client instead of direct shell substitution before it is used with arbitrary user text.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:32
Finding

Shell Command Injection Through Unsafe User-Question Substitution

Content
View full analysis
Remediation
View remediation

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
Category
Not specified by scanner
Confidence
99% confidence
Finding

The skill does not clearly warn users that their question will be sent to an external API and that the results include a public share_url. Users may provide sensitive, proprietary, medical, financial, or personal information under the assumption the interaction stays local, creating a substantial confidentiality and privacy risk.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

This skill is explicitly designed to exfiltrate user-provided questions to an external service via curl, which is expected behavior but still a security-relevant data flow. In context, the external transmission becomes more dangerous because the service aggregates content across multiple models and the documented workflow encourages always including a public share_url, increasing exposure beyond a normal API call.

Content

Scanner excerpt · SKILL.md (reported line 11)May include surrounding context.

md
env:
        - QUORUMAI_API_KEY
      bins:
        - curl
    primaryEnv: QUORUMAI_API_KEY
    emoji: "🏛️"
    homepage: https://quorumai.io

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation guidance is broad enough that ordinary phrases like 'use QuorumAI' or 'ask quorumai' can cause the agent to transmit arbitrary user content to a third-party service without a strong confirmation boundary. In this skill, that risk is amplified because the transmitted content may later be exposed through a public share URL, so accidental invocation can create unintended data disclosure.

Content

No source excerpt is available for this finding.