ClawHub
Back to skill

Security audit

Atlassian MCP (Jira, Confluence)

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate Atlassian MCP helper, but it hands Jira credentials to an unpinned third-party Docker container and enables agent-driven Jira actions without clear guardrails.

Install only if you trust the upstream Docker image and are comfortable giving an agent access to Jira or Confluence data. Use a dedicated least-privilege Atlassian account or token, avoid putting tokens directly in shell history or shared logs, pin the Docker image to a reviewed digest or version, and require explicit approval before any Jira create, update, delete, or project-management action.

SkillSpector

By NVIDIA
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 (1)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The documentation instructs users to pass Jira credentials and API tokens directly via environment variables and shell invocation, but it does not warn about secret exposure risks such as shell history, process inspection, terminal logging, CI logs, or accidental copy/paste into shared contexts. In a skill meant for agent integration, this omission increases the chance that sensitive Atlassian credentials are mishandled and later exposed or reused by unauthorized parties.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.