Back to skill

Security audit

越问越懂你的知识库机器人

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marked this skill suspicious because broad everyday triggers could route unrelated requests into a workflow that retrieves and saves information, and some referenced code was only partially inspected.

Consider whether broad activation and possible knowledge-base writes fit your use before installing. The scan was partial: two of four components were fully inspected and two only partially, so the evidence is incomplete. The verdict is suspicious, not a claim that the author acted maliciously.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

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
- 库里没有 → 懒吸收:公开静态页直接 WebFetch;SPA/登录墙用 `tools/fetch-url.js`(本地 Chrome 渲染)取,答完落节点、更新 INDEX

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 70)May include surrounding context.

md
- `tools/fetch-url.js` SPA/登录站抓取:本地 Chrome headless 渲染后取正文+链接;`--headful-login` 先真人登录(同 profile 下次免登)

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 69)May include surrounding context.

md
- `tools/check-kb.js` 校验全库(结构/字段/verified/链接/INDEX 双向/ASCII 名),发布前必跑

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, network, shell.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The trigger list includes everyday phrases without a knowledge-base scope requirement.

Medium
Category
Trigger Abuse
Confidence
98% confidence
Finding

The trigger “现在多少” is a generic everyday question fragment and does not require knowledge-base context, so unrelated requests can be routed into this skill. Because the documented workflow automatically retrieves missing information and persists answers, overly broad activation can cause unintended retrieval and knowledge-base writes, although no malicious takeover instruction is present.

Content

No source excerpt is available for this finding.

Internal Network Request

Medium
Category
Server-Side Request Forgery
Confidence
70% confidence
Finding

Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.

Content

Scanner excerpt · tools/fetch-url.js (reported line 123)May include surrounding context.

js
let ver = null;
  for (let i = 0; i < 30; i++) {
    await sleep(500);
    try { ver = await (await fetch('http://127.0.0.1' + port + '/json/version')).json(); break; } catch (e) { /* 端口没起,继续等 */ }
  }
  if (!ver) { console.error('CDP 调试口 15 秒没起来,重跑一次或检查端口占用'); cleanup(); process.exit(1); }