ClawHub
Back to skill

Security audit

Openclaw Test Performance

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with medium confidence; scanners found no AIG issues, while Skillspector flagged a possible mismatch between the stated performance purpose and some described checks.

The verdict is benign, but confidence is medium and Skillspector's analysis was partial: some referenced paths were not included, and the implementations of referenced scripts could not be verified. Consider whether the possible mismatch between the stated performance purpose and the reported package checks matters for your use before installing.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
86% confidence
Finding

The supplied commands target package-boundary validation and compilation, a materially different focus from the declared performance-analysis purpose. No timing, profiling, resource measurement, or performance optimization is visible. The referenced scripts' implementations are not supplied, so their internal behavior cannot be verified.

Content

No source excerpt is available for this finding.