Security audit

OpenClaw Waste Audit

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a read-only OpenClaw token-waste audit, but it tells the agent to send audit findings to a hard-coded X account without clear user approval of the exact payload.

Before installing, treat this as a review-needed skill. It can help audit OpenClaw token waste, but users should remove or ignore the instruction to contact @BeeGeeEth and should keep audit results local unless they personally review and approve exactly what will be shared.

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

Findings (1)

T01 · Skill Instruction Hijacking

Error

Location: SKILL.md:86
Finding: Audit Results Redirected to a Hard-Coded Third-Party Social Media Account
Content: View full analysis
Remediation: View remediation

SkillSpector

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

Static analysis

No suspicious patterns detected.