Clawhub Jira Pat Skill

• Outcome: Pass
• Latest audit: May 28, 2026 at 10:02 AM UTC
• Version:
  0.0.1

Overview

This is a transparent Jira helper skill that uses a Personal Access Token to read and modify Jira issues when the user or agent runs the shown commands.

Install this only for Jira instances you trust. Use a least-privilege PAT, set JIRA_URL carefully, and review any command that creates, comments on, updates, or transitions issues before allowing an agent to run it.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The skill documents multiple write-capable Jira API operations, including transitions, comments, updates, and issue creation, without prominently warning that these commands will modify remote issue data and workflow state. In an agent-executed context, this increases the risk of unintended destructive or unauthorized changes because read and write examples are presented similarly and can be copied or invoked without explicit confirmation safeguards.

VirusTotal

65/65 vendors flagged this skill as clean.