Back to skill

Security audit

Chips

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a skill for connecting OpenClaw to Chips that also includes a disconnect command; the verdict is benign because this purpose mismatch is the only contextual finding and the security dimensions are otherwise marked ok.

The scan was complete for the two reported components, and the verdict is benign with high confidence. Before installing, consider whether you want a skill whose reported capability includes disconnecting OpenClaw from Chips as well as its stated setup and connection purpose.

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
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
99% confidence
Finding

The command explicitly requests disconnection, which is materially opposite to the declared setup and connection purpose. No surrounding code indicates that this is a supporting step in a connection workflow.

Content

No source excerpt is available for this finding.