ClawHub
Back to skill

Security audit

企业工商信息查询

Security checks for vulnerabilities and agentic risk

Overview

This is a narrow Qixinbao business-information lookup skill with disclosed token and external API use, but users should handle the token carefully and verify fuzzy company matches.

Install only if you are comfortable sending queried company names or IDs to Qixinbao using your API token. Store the token like a password, avoid shared machines or screenshots, prefer company ID lookups for important decisions, verify the returned enterprise name, and update or pin axios before relying on this in a sensitive environment.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The skill instructs users to store a long-lived API token in a persistent environment variable and provides setup steps, but it does not warn about credential sensitivity, scope, rotation, or risks of exposing the token through logs, shell history, screenshots, or shared machines. While common, this increases the chance of accidental credential leakage and unauthorized API use if the host environment is compromised or misconfigured.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The documentation states that when only an enterprise name is provided and an exact match is unavailable, the system will automatically use the first search result. In a business verification skill, this can cause silent misidentification of the target company and lead users or downstream agents to rely on incorrect registration, status, or ownership data for compliance, contracting, or supplier screening decisions.

Unpinned Dependencies

Low
Category
Supply Chain
Content
"author": "",
  "license": "MIT",
  "dependencies": {
    "axios": "^1.6.0"
  },
  "devDependencies": {
    "@types/node": "^20.0.0",
Confidence
87% confidence
Finding
Using a caret range for axios allows future installs to resolve to different versions, which can introduce unreviewed behavior or newly published supply-chain compromise into the runtime dependency tree. In a skill that performs external business-information queries, HTTP client behavior is security-relevant because request handling, proxy logic, and response parsing directly affect trust boundaries.

Known Vulnerable Dependency: axios==1.6.0 — 10 advisory(ies): CVE-2025-62718 (Axios has a NO_PROXY Hostname Normalization Bypass that Leads to SSRF); CVE-2026-42044 (Axios: Invisible JSON Response Tampering via Prototype Pollution Gadget in `pars); CVE-2026-25639 (Axios is Vulnerable to Denial of Service via __proto__ Key in mergeConfig) +7 more

High
Category
Supply Chain
Confidence
98% confidence
Finding
The package depends on axios 1.6.0, which is flagged with multiple known advisories including SSRF-related proxy bypass and prototype-pollution/DoS issues. Because this skill likely performs outbound HTTP requests to enterprise-information services, a vulnerable HTTP client is especially dangerous: it can weaken network boundary assumptions, enable malformed-response attacks, or expose the host to denial of service under crafted inputs or hostile proxy environments.

Static analysis

No suspicious patterns detected.