Back to skill

Security audit

OzBargain Monitor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed OzBargain deal monitor that creates scheduled OpenClaw jobs and sends results to user-chosen destinations.

Before installing, confirm that you want OpenClaw to create recurring cron jobs, send deal summaries to the configured chat or group, and keep a local dedupe file of sent OzBargain links. For troubleshooting, confirm the destination before allowing any live probe message.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The troubleshooting instructions tell the agent to send a probe message directly to the configured destination without requiring an explicit user warning or approval. This can cause unintended outbound communication to real chats or groups, potentially leaking operational details, creating spam, or messaging the wrong recipient if the destination is stale or misconfigured.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The template explicitly sets 输出语言:<LANGUAGE>, which hard-codes the response language through configuration rather than offering the end user a language or locale choice. The policy for this audit flags language or locale constraints unless they are optional or clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill instructs the agent to create and update a user-specific local state file for deduplication, but it does not require any explicit user notice or confirmation before modifying local data. While the write target is narrowly scoped and operationally relevant, silent filesystem modification can violate user expectations and creates a persistence side effect that may matter in shared or sensitive environments.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.