T06 · System Persistence
- Location
setup-cron.js:23- Finding
Persistent Main-Session Instruction Injection Through Scheduled Jobs
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
The skill openly builds an autonomous learning loop, but it installs persistent agent-facing schedules and can modify memory, task queues, and generated skills with weak safeguards.
Install only if you intentionally want persistent autonomous agent behavior. Review setup-cron.js and the engine scripts first, avoid enabling cron until you understand every scheduled job, keep the workspace private, and do not trust auto-generated skills without manual review.
setup-cron.js:23Persistent Main-Session Instruction Injection Through Scheduled Jobs
setup-cron.js:53Shell Command Injection Through Unescaped Cron Configuration
engines/learning-direction.js:194Task-Controlled Command Injection in Skill Discovery
engines/learning-direction.js:203Execution of an Undeclared and Unpinned Package Through npx
engines/evolution-engine.js:99Recurring Modification of Shared Agent Memory
engines/skill-creator.js:96Unsanitized Workspace Content Embedded Into Generated Skill Instructions
Referenced artifact was not completely inspected
| **进化引擎** | 任务选择 + 自主执行 | `engines/evolution-engine.js` |
Referenced artifact was not completely inspected
| **进化引擎** | 任务选择 + 自主执行 | `engines/evolution-engine.js` |
Referenced artifact was not completely inspected
| **进化引擎** | 任务选择 + 自主执行 | `engines/evolution-engine.js` |
Referenced artifact was not completely inspected
| **进化引擎** | 任务选择 + 自主执行 | `engines/evolution-engine.js` |
Referenced artifact was not completely inspected
| **进化引擎** | 任务选择 + 自主执行 | `engines/evolution-engine.js` |
Referenced artifact was not completely inspected
| **进化引擎** | 任务选择 + 自主执行 | `engines/evolution-engine.js` |
Referenced artifact was not completely inspected
| **学习提取器** | 从任务提取可复用模式 | `engines/extractor.js` |
Referenced artifact was not completely inspected
| **自信度评估** | 计算模式可靠性评分 | `engines/confidence.js` |
Referenced artifact was not completely inspected
| **技能创建器** | 高自信模式→可复用技能 | `engines/skill-creator.js` |
Referenced artifact was not completely inspected
| **反思引擎** | 每日/每周反思报告 | `engines/reflection.js` |
Referenced artifact was not completely inspected
| **反思引擎** | 每日/每周反思报告 | `engines/reflection.js` |
Referenced artifact was not completely inspected
| **反思引擎** | 每日/每周反思报告 | `engines/reflection.js` |
Referenced artifact was not completely inspected
| **反思引擎** | 每日/每周反思报告 | `engines/reflection.js` |
Referenced artifact was not completely inspected
| **反思引擎** | 每日/每周反思报告 | `engines/reflection.js` |
Referenced artifact was not completely inspected
| **反思引擎** | 每日/每周反思报告 | `engines/reflection.js` |
Referenced artifact was not completely inspected
| **学习方向生成** | 自主发现新方向 + 生成任务 | `engines/learning-direction.js` |
Referenced artifact was not completely inspected
| **学习方向生成** | 自主发现新方向 + 生成任务 | `engines/learning-direction.js` |
Referenced artifact was not completely inspected
| **学习方向生成** | 自主发现新方向 + 生成任务 | `engines/learning-direction.js` |
Referenced artifact was not completely inspected
| **学习方向生成** | 自主发现新方向 + 生成任务 | `engines/learning-direction.js` |
The document directly instructs users to install the skill and execute init, cron-setup, and startup scripts without any warning, review guidance, or description of side effects. Because these commands can modify the local environment and establish persistent scheduled execution, a user could be induced to run unreviewed code and silently enable ongoing automated behavior on their system.
The document promotes autonomous scheduled execution, auto skill creation, and reflection loops without any explicit warning about what actions may occur automatically, what files may be modified, or how a user can constrain or disable those behaviors. In the context of an agent skill, this can lead users to enable persistent automation they do not fully understand, increasing the risk of unintended file changes, scheduled task registration, or other impactful side effects.
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
# 1. 创建 GitHub 仓库
gh repo create autonomous-learning-cycle --public
# 2. 添加文件
cd skills/autonomous-learning-cycle
The release notes advertise a 17-minute autonomous loop, automatic task execution, daily/weekly reflection, and automatic skill creation without clearly warning that the system may persistently modify files, consume resources, and change system behavior over time. In a self-modifying or self-extending agent skill, omission of these warnings materially increases the risk that users enable ongoing automation without informed consent or adequate safeguards.
The quick-start instructions tell users to run initialization, cron setup, and start commands, but do not warn that this creates persistent background execution. That can lead users to unknowingly install recurring jobs that continue running, consuming resources and potentially performing autonomous actions long after the initial setup.
The workflow advertises automatic task execution, pattern extraction, and automatic skill creation, but it does not warn that these actions may create or modify local files, configurations, reports, or generated artifacts. Because the skill is explicitly self-modifying in behavior and output generation, failing to disclose filesystem-side effects increases the risk of unreviewed changes and trust in machine-generated artifacts.