ClawHub
Back to skill

Security audit

full-stack-dev-expert

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a full-stack development skill with no AIG findings and four low-probability, purpose-expected Skillspector findings; the verdict is benign, with notes about setup commands and an unpinned tool reference.

The verdict is benign, not a guarantee of zero risk. Before installing, review any quick-start commands before running them, and check the destination and contents of API examples before using real credentials or data. The `npx shadcn` reference is unpinned, so its downloaded version may change.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

The documentation workflow requires executing the project's quick-start steps without warning the user about possible system or data changes.

Medium
Category
Output Handling
Confidence
86% confidence
Finding

Step 5 instructs the documentation agent to personally follow the quick-start procedure, or have a developer do so. This moves beyond writing documentation into running project-specific setup and startup commands, but the file does not warn that verification may install dependencies, modify local configuration or databases, or start services.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx shadcn'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · templates/api-contract.md (reported line 43)May include surrounding context.

  • 示例（可复制粘贴，含认证头）：
bash
curl -X POST "$BASE/api/v1/..." -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" -d '{}'

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · templates/deploy-guide.md (reported line 29)May include surrounding context.

6. 启动

<命令>

7. 验证

curl http://localhost/health # 预期输出：...

text

## 3. Docker 方式（如提供）