Back to skill

Security audit

Cross-Session Task Manager

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed local task-memory template system, with persistence that matches its stated purpose and no evidence of network access, credential handling, hidden code, or destructive behavior.

Before installing, make sure you want the agent to keep task notes under ~/.openclaw/workspace and to check ACTIVE-TASKS.md across sessions. Avoid putting secrets or sensitive private details in these task files, and review AGENTS.md changes so the persistence behavior matches your expectations.

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
  • 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
Findings (6)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The natural-language description and operational instructions are presented as Chinese-only behavior, including trigger wording and required file content guidance, with no indication that users may choose another language. This can violate language/locale policy where skills should not impose a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are very broad and include generic concepts like task management, session memory, and continuity, which can cause the skill to activate in contexts the user did not explicitly intend. Unintended invocation is risky here because the skill instructs the agent to read and update persistent workspace files, expanding data access and behavior beyond the immediate request.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
95% confidence
Finding

This duplicate finding points to the same persistence behavior: the agent is directed to maintain a workspace, create project directories, and automatically resume tasks from prior sessions. In a skill specifically designed for continuity, that increases the risk of stale, incorrect, or sensitive context being resurrected in later interactions, especially across channels/threads where the user may not expect memory.

Content

Scanner excerpt · SKILL.md (reported line 31)May include surrounding context.

1. 复制模板到你的 workspace

cp templates/ACTIVE-TASKS.md ~/. openclaw/workspace/ cp templates/CLOSED-TASKS.md ~/.openclaw/workspace/ mkdir -p ~/.openclaw/workspace/projects/

2. 在 AGENTS.md 中添加规则(见下方)

text

Session Persistence

Medium
Category
Rogue Agent
Confidence
95% confidence
Finding

This duplicate finding points to the same persistence behavior: the agent is directed to maintain a workspace, create project directories, and automatically resume tasks from prior sessions. In a skill specifically designed for continuity, that increases the risk of stale, incorrect, or sensitive context being resurrected in later interactions, especially across channels/threads where the user may not expect memory.

Content

Scanner excerpt · SKILL.md (reported line 31)May include surrounding context.

1. 复制模板到你的 workspace

cp templates/ACTIVE-TASKS.md ~/. openclaw/workspace/ cp templates/CLOSED-TASKS.md ~/.openclaw/workspace/ mkdir -p ~/.openclaw/workspace/projects/

2. 在 AGENTS.md 中添加规则(见下方)

text

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file contains user-facing operational instructions entirely in Chinese, including the title, description, status definitions, archiving rules, and usage guidance. Under the policy for natural-language violations, forcing a specific language without user opt-in is a locale/language policy issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown template presents all user-facing headings and checklist text in Chinese only, with no indication that other languages are supported or that Chinese is optional. That can violate language/locale policy when a skill forces a specific language without user opt-in.

Content

No source excerpt is available for this finding.