ClawHub
Back to skill

Security audit

lantern-works

Security checks for vulnerabilities and agentic risk

Overview

The skill provides public GPU-price and deal lookups with disclosed referral links and an optional local installation.

Prefer the hosted service or public JSON API. If using the local alternative, review and pin its package version. Keep private information out of submitted workload descriptions, and check vendor pricing dates and disclosed referral links.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

MCP server referenced without pinned version: 'uvx lantern-works-deals-mcp'.

Medium
Category
MCP Rug Pull
Confidence
96% confidence
Finding

The optional local command uvx lantern-works-deals-mcp can download and execute an unpinned package release, allowing a compromised publisher account or malicious future release to run code with the agent process's permissions. The public, read-only purpose does not restrict that local code's access to files, credentials, or the network, although the hosted MCP and JSON API alternatives make this exposure avoidable.

Content

No source excerpt is available for this finding.