ClawHub
Back to skill

Security audit

Rentaclaw

Security checks across malware telemetry and agentic risk

Overview

This appears to be a Rentaclaw marketplace helper, but it can use account credentials to change live listings without clear enough safety guardrails.

Review before installing. Use this only if you intend the agent to manage Rentaclaw listings, configure a narrowly scoped webhook/token, keep those environment variables out of unrelated sessions, and require explicit confirmation for any command that changes listings, prices, or availability.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill declares use of sensitive environment variables and outbound network access in metadata, but the finding indicates these capabilities are not formally declared in a permissions model. That mismatch weakens review and consent boundaries because operators may not get a clear, enforceable understanding that the skill can access secrets and transmit them to an external service.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The README documents commands that can pause, resume, and update live marketplace listings, but it does not clearly warn users that these are state-changing actions against real Rentaclaw accounts. In an agentic context, ambiguous natural-language commands can be issued accidentally or by prompt injection, so missing safety language increases the chance of unintended marketplace changes and financial or reputational harm.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.