Back to skill

Security audit

OpenClaw 新手训练营

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent OpenClaw onboarding tutorial skill that demonstrates search, file, cron, skills, and channel features, with some ordinary side effects users should notice.

Before installing, expect this skill to guide users through real OpenClaw actions: searches, a sample file write, scheduled reminders, skill/channel listing, and memory progress tracking. Use it in a test or low-risk workspace if you do not want a possible notes.md file or cron reminder left behind, and exit the bootcamp if it triggers unexpectedly.

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
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger set includes generic phrases like “教学” and “bootcamp”, which can appear in ordinary conversation and cause the skill to activate unexpectedly. Because the skill is marked always=true and leads users into operational flows involving search, file access, cron, and environment disclosure, accidental activation can expose capabilities or prompt actions the user did not intend.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The file-operations stage instructs the agent to write notes.md and later read it back, but does not clearly warn the user beforehand that the workspace will be modified. Unexpected file creation can overwrite existing files, create confusion about persistence, and normalize write operations without informed consent, which is riskier in a tutorial aimed at new users.

Content

No source excerpt is available for this finding.