Back to skill

Security audit

Alter Manager

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently manages OpenClaw sub-sessions and its file access, routing state, and deletion behavior are disclosed and tied to that purpose.

Install this if you want an agent helper that can manage OpenClaw sub-sessions. Be aware it may read local OpenClaw session metadata, create and route messages to sub-sessions, persist the current routing target in the workspace, and delete selected sessions after confirmation while archiving their transcripts.

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
93% confidence
Finding

The trigger description is overly broad, covering generic requests like managing multiple conversations or creating independent sessions without strong disambiguation. This can cause unintended skill activation during normal dialogue, leading the agent to read local session state, create/delete sessions, or enter routing mode when the user did not explicitly request those operations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

整个技能描述与示例均以中文固定呈现,并在用户交互示例中默认中文回复,但文件中没有说明这是可选语言,也没有给出用户可选择其他语言的机制。按规则,这属于语言/locale 约束未取得用户选择的自然语言策略问题。

Content

No source excerpt is available for this finding.