Back to skill

Security audit

旺小宝 HTML 发布

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious with medium confidence, mainly because it reports a possible path for excluded files to be included in a public upload and could not fully inspect several scripts.

Consider the reported public-upload risk before installing. Skillspector reports only 37.5% complete coverage, with five files partially inspected, so the evidence is incomplete and the OK statuses should not be read as assurance of safety.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/site.mjs
Finding

HTML and CSS references bypass sensitive-file exclusions

Content
View full analysis

Impact

If the publication proceeds, the excluded file's contents are uploaded to the public storage service under their original relative path. Neither manifest integrity checks nor the public-upload flag distinguish attacker-added local-file references from intended assets.

Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

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 60)May include surrounding context.

md
只有 `site.mjs prepare/publish` 这一套执行流程:指定源目录 → 临时副本路径转换 → 逐文件上传 → 验证。`publish.mjs` 仅提供上传协议函数,不是另一个命令入口。

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

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.