ClawHub
Back to skill

Security audit

YouTrack Issue Tracker

Security checks for vulnerabilities and agentic risk

Overview

This YouTrack helper is a straightforward issue-management skill, but it relies on a local API token and includes bulk issue changes that users should handle carefully.

Install only if you are comfortable giving the agent access to your YouTrack instance. Use a least-privilege token, store it carefully, and run bulk commands with narrow queries and --dry-run first because they can change many issues.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill explicitly documents storing a long-lived YouTrack API token in a local config file or environment variables but provides no guidance on secure handling, least privilege, file permissions, rotation, or avoiding accidental disclosure. In an agent/CLI context, these credentials can be exposed through logs, shell history, backups, process environments, or over-broad filesystem access, enabling unauthorized issue access or modification.

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The skill advertises bulk-update, bulk-comment, and bulk-assign commands that can modify many issues at once, but it does not clearly warn that these operations may have wide-reaching, hard-to-reverse effects if a query is too broad or mis-specified. Although some examples include --dry-run, the documentation does not position it as a required safety step or describe confirmation safeguards, increasing the chance of accidental mass changes.

Static analysis

No suspicious patterns detected.