ClawHub
Back to skill

Security audit

雄韬CRM - 官网自动化精准营销

Security checks for vulnerabilities and agentic risk

Overview

This skill documents a website publishing API and clearly warns that changes go live, need confirmation, and require a read-write token.

Install only if you intend the agent to help publish or edit live website content. Treat the token as sensitive, confirm the exact site and content before writes, use draft or hidden fields for unfinished articles/products, and remember cases do not have a draft switch and the API has no delete endpoint.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The manifest description lists trigger phrases such as “发文章”, “上架产品”, and “更新官网内容” without clear scoping constraints or exclusion examples. These phrases are generic enough to match ordinary conversation about website work, which could cause unintended invocation outside a narrowly defined command context.

External Transmission

Medium
Category
Data Exfiltration
Content
- 成功条目的 `slug` 冲突时自动加 `-2`、`-3`…

```bash
curl -s "$WEBSITE_API_BASE/website.post/add" \
  -H "Authorization: Bearer $WEBSITE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"items":[
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.