ClawHub
Back to skill

Security audit

BenchmarkONE

Security checks for vulnerabilities and agentic risk

Overview

This BenchmarkONE connector is mostly coherent, but it tells the agent to install its CLI by executing a remote script directly in the shell if the CLI is missing.

Review the installer step before using this skill. Prefer installing the oo CLI from official documentation with normal verification, and only let the agent run BenchmarkONE write actions after you have checked the exact contact changes it plans to make.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

The skill instructs the agent to install software by piping a remotely fetched script directly into a shell (curl ... | bash). This is dangerous because it executes code from the network without integrity verification, exposing the environment to supply-chain compromise, MITM risks, or malicious changes on the hosting server.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The manifest description defines activation in very broad terms: "ANY BenchmarkONE request" and "Whenever a task involves BenchmarkONE." This lacks boundaries or exclusion conditions, so it could match many ordinary BenchmarkONE-related conversations beyond intended connector operations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.