Back to skill

Security audit

直播电商日报

Security checks for vulnerabilities and agentic risk

Overview

This Chinese-language live-commerce reporting skill searches public industry sources and saves a local daily report, and those behaviors are disclosed and fit its purpose.

Install this if you want a Chinese live-commerce daily report and are comfortable with the agent using web search, reading yesterday's saved report in the configured folder, remembering your report preferences if the host supports that, and writing Markdown or HTML files to the chosen local path.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
78% confidence
Finding

The README presents the skill name, trigger phrase, and all interaction examples exclusively in Chinese, and the trigger appears language-specific. Under the policy, forcing a specific language without opt-in can be a natural-language policy violation unless the locale restriction is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

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.

Content

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

bash
# WorkBuddy 用户
mkdir -p ~/.workbuddy/skills/ecom-daily-report
cp SKILL.md ~/.workbuddy/skills/ecom-daily-report/

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 22)May include surrounding context.

md
### 安装方法

1. 将本文件(`SKILL.md`)放入你的 Skill 目录:
   - WorkBuddy:`~/.workbuddy/skills/ecom-daily-report/SKILL.md`
   - 其他工具:参考各自的 Skill 安装文档
2. 重启 AI 工具 或 刷新 Skill 列表
3. 输入 `今日直播电商日报` 即可触发

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The documentation says users can specify '保存到 ~/Documents/' and later states that the report is automatically saved as a Markdown file locally. Because this behavior affects user data and filesystem state, the skill description should explicitly disclose that it creates or overwrites files on disk.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown file states that the skill will '优先抓取' content from external platforms such as 36氪、今日头条 and 微博, which implies network requests and transmission of user/system context to third-party services. The README explains the feature but does not explicitly warn users about external access or privacy implications.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The HTML template hard-codes lang="zh-CN", which specifies a single locale for generated output. The document does not indicate that users can choose another language or locale, so this is a natural-language locale policy constraint without opt-in.

Content

No source excerpt is available for this finding.