ClawHub
Back to skill

Security audit

varg-character-fitness

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign with medium confidence: scanners found an unpinned install command and a possible mismatch between the fitness-character purpose and broader plugin setup, while the completed AIG scan reported no findings.

The verdict is benign, but consider that the installer may run a changeable version of the `skills` package and may offer a much broader 83-skill plugin. Skillspector’s analysis was partial, so the results do not fully establish what the installed skill does.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The supplied chunk is an installation guide, not an implementation of the declared character-design workflow. Its commands install skills or plugins and modify agent tooling configuration; none creates a character sheet, maintains appearance consistency, or prepares workout scenes. Installing the named skill could support the declared purpose, but the supplied chunk itself only performs setup and also offers installation of a substantially broader bundle. This assessment is limited to the provided commands and does not establish what the installed skill actually does.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The installation command invokes an unpinned npm CLI through npx skills, allowing the package version executed during installation to change over time. Although this is not an MCP server reference as labeled, it is a supply-chain risk: a compromised future package release could execute with the installing user's permissions.

Content

No source excerpt is available for this finding.