ClawHub
Back to skill

Security audit

varg-character-absurd

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign with medium confidence: scanners reported an unpinned `npx skills` installer as a supply-chain risk, and one local reference could not be resolved.

If you install, consider whether you trust the `npx skills` installer and pin it to a reviewed version where possible. The scan is incomplete: a local reference in SKILL.md could not be resolved, so the verdict does not establish that the artifact is risk-free.

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

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

The installation command invokes the unpinned skills npm package through npx, potentially fetching and executing a changing package version with the user's privileges. Although the scanner incorrectly describes this as an MCP server reference, the underlying supply-chain risk is real: a compromised future release could execute malicious code during installation. This is ordinary installation documentation rather than evidence of malicious intent, and exploitation requires someone to run the command.

Content

No source excerpt is available for this finding.