ClawHub
Back to skill

Security audit

Jev AI Model Evaluator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent AI model evaluation helper, with the main caution that its optional MCP setup uses an unpinned GitHub-based npx install.

Reasonable to install for evaluation planning, but only enable the optional MCP if you trust the GitHub repository or can pin/review the exact version. Do not treat its model recommendations as authoritative without your own tests and current pricing/version checks.

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 (2)

Rp1

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

The skill instructs users to install and run an MCP server directly from a GitHub reference via npx -y github:... without pinning to an immutable version, tag, or commit. That creates a supply-chain risk: if the upstream repository changes or is compromised, users could execute unexpected code locally under the guise of following the skill instructions.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 62)May include surrounding context.

md
- About: https://jevaimodel.org/en/about
- Privacy: https://jevaimodel.org/en/privacy-policy
- Terms: https://jevaimodel.org/en/terms-of-service
- Raw Skill: https://jevaimodel.org/skills/jev-ai-model-evaluator/SKILL.md
- MCP source: https://github.com/gpt-img-2/jev-ai-model-evaluation-mcp
- ClawHub listing: https://clawhub.ai/gpt-img-2/skills/jev-ai-model-evaluator

Static analysis

No suspicious patterns detected.