ClawHub
Back to skill

Security audit

Query-Skills

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent skill-search tool, with privacy and dependency hygiene issues but no evidence of hidden persistence, credential theft, destructive behavior, or malicious data exfiltration.

Install only if you are comfortable with search terms being sent to ClawHub and, on fallback, to skills.volces.com. Avoid pasting secrets or private project names as queries, and prefer an updated release that removes raw query logging and upgrades/pins axios.

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 (3)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The search method logs the detected language, raw query, and translated query directly to the console. Search queries can contain sensitive user data, internal project names, credentials pasted by mistake, or other private terms, so verbose logging creates a confidentiality risk if logs are retained, aggregated, or exposed to operators and third parties.

Unpinned Dependencies

Low
Category
Supply Chain
Content
"author": "",
  "license": "MIT",
  "dependencies": {
    "axios": "^1.6.8"
  },
  "devDependencies": {}
}
Confidence
89% confidence
Finding
Using a caret range for axios (^1.6.8) is a supply-chain risk because installs may resolve to different versions over time, reducing reproducibility and potentially pulling in a newly introduced vulnerable release. In a skill that performs external search across multiple sources, HTTP client behavior is security-relevant, so dependency drift increases operational risk.

Known Vulnerable Dependency: axios==1.6.8 — 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
97% confidence
Finding
The dependency is explicitly set to axios 1.6.8, which is reported by the finding as having multiple known advisories, including SSRF bypass and prototype-pollution-related issues. Because this skill is intended to search/discover content from multiple sources, it likely makes outbound requests; in that context, a vulnerable HTTP client is more dangerous because request routing, proxy handling, or response parsing weaknesses may be reachable.

Static analysis

No suspicious patterns detected.