Back to skill

Security audit

SonarCloud Management Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed SonarCloud/SonarQube management guide with high-impact project actions, but I found no hidden execution, persistence, exfiltration, or deceptive behavior.

Install only if you intend to let an agent manage Sonar projects with your token. Use read-only commands first, require explicit approval before resolving issues, marking false positives, changing gates/profiles/settings/tags, or using raw API calls, and note that the referenced helper script was not present in the inspected package.

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
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill description is broad enough to activate on many general Sonar-related requests, including high-impact actions such as closing issues, marking findings false-positive, changing quality gates, modifying settings, and performing raw API calls. Overbroad activation increases the chance the agent invokes this skill in situations where the user intent is ambiguous, which can lead to inappropriate security-triage decisions or unauthorized configuration changes if the surrounding agent framework does not enforce strong confirmation and scoping.

Content

No source excerpt is available for this finding.