Back to skill

Security audit

奇妙生产力

Security checks for vulnerabilities and agentic risk

Overview

The skill coherently provides remote file-production services, with disclosed uploads, optional account access, and explicit approval for each purchase.

Upload only materials you intend the remote provider to process. Check each order and exact price before confirming; chat confirmation can directly authorize a balance payment. Keep task credentials and private output links out of public logs. Remote data retention and current server behavior remain unverified.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 30)May include surrounding context.

md
node scripts/mcp.mjs overview

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

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

md
node scripts/mcp.mjs tools

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 32)May include surrounding context.

md
node scripts/mcp.mjs call get_tool <<'JSON'

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 37)May include surrounding context.

md
`tools` 返回原生工具 schema;其他调用使用 `node scripts/mcp.mjs call TOOL_NAME`,通过标准输入传入一个符合 schema 的 JSON 对象。不要将私有凭据放进命令行参数或提交到仓库。该调用器不保存会话、材料或业务凭据,不会代替用户作出确认。用户在对话里明确确认本单金