Back to skill

Security audit

Dark Factory Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill appears aimed at a real multi-agent startup workflow, but its setup path depends on unpinned external code and an unavailable setup script that users cannot review from the artifact.

Install only if you are comfortable reviewing the setup script and external dependencies yourself. Prefer pinning the ClawHub installer version and ChatDev commit, run setup from a low-privilege environment, and avoid exposing unnecessary product repositories or API keys until the installed files and scripts are inspected.

Vulnerability Patterns
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (2)

T08 · Insecure Dependencies

Error
Location
SKILL.md:61
Finding

Execution of an Unpinned Package Through npx

Content
View full analysis
Remediation
View remediation

T03 · Remote Payload Retrieval and Execution

Warning
Location
SKILL.md:56
Finding

Automatic Retrieval of an Unpinned Remote Repository

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The skill instructs users to execute npx clawhub@latest install dark-factory, which fetches and runs remote package code without pinning to a specific reviewed version. Using @latest creates a moving trust boundary: a compromised publisher account, malicious update, or dependency hijack could result in arbitrary code execution on the user's system during installation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill tells the user to run bash scripts/setup-dark-factory-v2.sh without describing what the script does, what system changes it makes, or warning that it may execute external code and modify the environment. In this skill's context, the script appears to install and configure a multi-agent platform with external integrations, which increases the risk of opaque system modification, dependency installation, credential exposure, or execution of unreviewed code.

Content

No source excerpt is available for this finding.