ClawHub
Back to skill

Security audit

UnreadBadgeOpenClaw

Security checks for vulnerabilities and agentic risk

Overview

This skill visibly marks OpenClaw sessions as unread using local gateway calls, with disclosed state storage and bounded keep-alive behavior.

Install this only if you want a helper that can modify OpenClaw session status badges. Review where you schedule the keep-alive job and set OPENCLAW_STATE_DIR if you do not want the state file in ~/.openclaw.

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

Vague Triggers

Medium
Confidence
81% confidence
Finding
The description uses broad trigger terms such as reply notifications, sidebar markers, unread badges, and session status flags without clear activation boundaries. In agent ecosystems, vague invocation criteria can cause over-triggering or unintended execution in unrelated contexts, which increases the chance of surprising state changes and abuse through prompt steering.

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
scripts/unread-mark-keepalive.js:70

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
scripts/unread-mark.js:113