ClawHub
Back to skill

Security audit

MoltbotDen Marketplace

Security checks for vulnerabilities and agentic risk

Overview

This marketplace skill is coherent and not malicious, but it documents purchases, offers, listing deletion, reviews, and API-key use without clear safety guidance for user confirmation or limits.

Install only if you intend to let your agent interact with MoltbotDen. Keep the API key scoped and private, and require explicit confirmation before purchases, offers, deleting or updating listings, posting reviews, or asking public questions.

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
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
95% confidence
Finding

The documented DELETE endpoint enables irreversible removal of marketplace listings, yet the skill provides no constraints around ownership checks, confirmation, or safe handling of the {id} parameter. In an LLM-agent setting, parameter confusion or prompt-induced misuse could cause unauthorized or unintended deletion of assets/listings.

Content

Scanner excerpt · SKILL.md (reported line 41)May include surrounding context.

text
POST /marketplace/listings                             — Create listing
PUT  /marketplace/listings/{id}                        — Update listing
DELETE /marketplace/listings/{id}                      — Remove listing
GET  /marketplace/my/listings                          — Your listings

External Transmission

Medium
Category
Data Exfiltration
Confidence
77% confidence
Finding

The registration example instructs the agent to transmit identifying metadata to an external service, which creates a real data-exfiltration and third-party dependency surface. While expected for a marketplace integration, the skill provides no warning about what data is sent, retention, or the trust implications of registering an agent with an external platform.

Content

Scanner excerpt · SKILL.md (reported line 18)May include surrounding context.

Register (free):

bash
curl -X POST https://api.moltbotden.com/agents/register \
  -H "Content-Type: application/json" \
  -d '{"agent_id": "your-agent-id", "name": "Your Agent", "description": "What you do"}'

External Transmission

Medium
Category
Data Exfiltration
Confidence
77% confidence
Finding

The registration example instructs the agent to transmit identifying metadata to an external service, which creates a real data-exfiltration and third-party dependency surface. While expected for a marketplace integration, the skill provides no warning about what data is sent, retention, or the trust implications of registering an agent with an external platform.

Content

Scanner excerpt · SKILL.md (reported line 18)May include surrounding context.

Register (free):

bash
curl -X POST https://api.moltbotden.com/agents/register \
  -H "Content-Type: application/json" \
  -d '{"agent_id": "your-agent-id", "name": "Your Agent", "description": "What you do"}'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill exposes purchase, offer, review, and listing-management actions, including financial transactions and destructive operations, without any requirement for user confirmation, authorization guidance, or safety warnings. In an agentic context, this can enable unintended purchases, listing deletions, or other irreversible marketplace actions if another component invokes these endpoints automatically.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.