Security audit

Sonarqube Analyzer

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent SonarQube analysis integration with weak credential guidance and confusing auto-fix wording, but no evidence of hidden writes, persistence, exfiltration, or destructive behavior.

Install only if you intend to connect an agent or CLI to your SonarQube instance. Use a real least-privilege SonarQube token from environment or secret storage, do not commit tokens, and review any future version carefully if it adds real auto-fix behavior that writes to source files.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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

Findings (4)

Missing User Warnings

Medium

Confidence: 86% confidence
Finding: The skill advertises automatic fixes via `autoFix` and `--suggest-fixes` but does not clearly warn that these actions may modify repository files. In an agentic context, this can lead to unintended code changes, especially if a user assumes the tool is read-only or runs it in CI without safeguards.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The documentation includes an authentication token example (`SONAR_TOKEN=admin`) without any credential-handling warning, which normalizes insecure secret usage and may encourage hardcoded or weak credentials. In practice, users may copy this configuration directly, exposing access to the SonarQube instance or training agents to reveal or reuse secrets unsafely.

Vague Triggers

Low

Confidence: 89% confidence
Finding: The tool descriptions are generic enough that an agent may invoke them without strong contextual checks, especially for project-wide issue retrieval or analysis actions. While not directly exploitable on its own, this increases the chance of over-broad or unintended tool use, which can expose project metadata or trigger analysis actions in situations the user did not clearly request.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The manifest advertises an 'autoFix' capability that may modify code, but it does not include a clear user-facing warning about code changes, review requirements, or possible side effects. In an agent setting, this can lead to silent or insufficiently reviewed modifications that introduce functional regressions, security issues, or unwanted repository changes.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.env_credential_access, suspicious.install_untrusted_source

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: src/api.js:6

Install source points to URL shortener or raw IP.

Warn

Code: suspicious.install_untrusted_source
Location: openclaw.plugin.json:118

Install source points to URL shortener or raw IP.

Warn

Code: suspicious.install_untrusted_source
Location: package.json:57