Back to skill

Security audit

Ucts Investigate

Security checks for vulnerabilities and agentic risk

Overview

This is a lightweight debugging-methodology skill with no executable code, persistence, credential access, or hidden data movement.

Safe to install for guided debugging. Be aware that the skill may suggest moving into Claude Code when hands-on code inspection, test execution, or edits are needed, despite the short description saying OpenClaw alone is enough.

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

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest description explicitly says the skill 'Works directly in OpenClaw — no Claude Code session needed.' However, the later instructions say that if investigation requires reading code, running tests, or making changes, the user should 'Load UCTS' and run /investigate in Claude Code. That is a direct behavior/scope mismatch in how the skill is intended to be used.

Content

No source excerpt is available for this finding.