Security audit

Agent Orchestrator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward multi-agent task orchestrator, with the main privacy caveat that task content may be shared among sub-agents.

Install only if you are comfortable with complex tasks being split across sub-agents. Avoid using it with secrets, regulated data, private sales data, or sensitive code unless your OpenClaw environment and sub-agent sharing rules are approved for that data.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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 (1)

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The skill explicitly promotes spawning multiple sub-agents and passing them task-specific instructions, but it does not warn users that their prompt content and possibly sensitive task data may be propagated to parallel sub-agents. This creates a real transparency and privacy risk because users may unknowingly trigger broader data exposure than intended, especially in research, code review, or internal business analysis workflows.

Static analysis

No suspicious patterns detected.