ClawHub
Back to skill

Security audit

Harness Control Layer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed planning and routing aid for OpenClaw workflows, with no executable payload or hidden persistence found.

Install this if you want a high-level control layer for routing OpenClaw work and adding safety/verification checkpoints. Review whether you want such a broad routing skill active by default in your setup, especially for sensitive operations, but the inspected artifacts do not show hidden execution, exfiltration, or persistence.

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
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • 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)

Memory Manipulation

High
Category
Memory Poisoning
Confidence
85% confidence
Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · SKILL.md (reported line 8)May include surrounding context.

md
# Harness Control Layer

Use this skill to make large OpenClaw setups more deterministic. Harness should sit above existing OpenClaw surfaces as an operational control layer. It should route, classify, verify, and record. It should not replace memory, context, skills, or execution policy.

## Core Boundary

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The default prompt uses a very broad invocation phrase for routing generic OpenClaw tasks, which can unintentionally match ordinary user requests and trigger this control-layer skill outside its intended scope. Because this skill is designed to influence routing, memory surfaces, safety preflights, and verification behavior across many other skills, accidental activation can alter task handling or bypass more specific skill-selection boundaries.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.