Back to skill

Security audit

agents efficient workflow

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed workflow guide for targeted agent handoffs and local markdown state, with manageable privacy considerations around saved handoff files.

Install only if you want agents to create durable local handoff notes for multi-agent work. Avoid putting secrets or unnecessary private data in handoff files, and periodically clean up ~/.openclaw/shared-handoffs/ if the retained context is no longer needed.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill presents core instructions throughout in both English and Chinese, but it does not state that multilingual output is optional or based on user preference. Under the policy rule for language/locale, forcing or assuming a specific language format without opt-in can be a natural-language policy issue.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
91% confidence
Finding

This duplicate finding points to the same behavior: writing markdown handoff files into a shared directory. Shared persistence can leak confidential task details, enable unintended data reuse, or allow downstream agents to trust stale or tampered context, especially because the skill treats local files as the source of truth.

Content

Scanner excerpt · SKILL.md (reported line 61)May include surrounding context.

md
### 2. Persist the handoff locally before transfer | 交接前先把信息落到本地

Before asking another agent to continue, write a markdown handoff file in the shared handoff directory.
在让另一个 agent 接手前,先在共享交接目录写好 Markdown 交接文件。

Default shared directory / 默认共享目录:

Session Persistence

Medium
Category
Rogue Agent
Confidence
91% confidence
Finding

This duplicate finding points to the same behavior: writing markdown handoff files into a shared directory. Shared persistence can leak confidential task details, enable unintended data reuse, or allow downstream agents to trust stale or tampered context, especially because the skill treats local files as the source of truth.

Content

Scanner excerpt · SKILL.md (reported line 61)May include surrounding context.

md
### 2. Persist the handoff locally before transfer | 交接前先把信息落到本地

Before asking another agent to continue, write a markdown handoff file in the shared handoff directory.
在让另一个 agent 接手前,先在共享交接目录写好 Markdown 交接文件。

Default shared directory / 默认共享目录:

Static analysis

No suspicious patterns detected.