ClawHub
Back to skill

Security audit

Jira

Security checks across malware telemetry and agentic risk

Overview

This Jira skill does what it claims, using your Jira API token for documented issue and worklog actions, including live Jira changes when you run write commands.

Install only if you trust the publisher with access to your Jira account. Use a least-privileged Jira token or account, set JIRA_BOARD when practical, and review any command that creates issues, changes status, assigns users, comments, or logs work because those changes persist in Jira.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding
The skill invokes shell-based functionality and external tooling (`curl`, `jq`, `python3`) but does not declare permissions or clearly scope what privileged actions it can perform. This creates a trust and review gap: operators may approve or run the skill without understanding that it can make authenticated API calls that read and modify Jira data.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill exposes multiple state-changing operations against Jira, including status changes, assignment, commenting, issue creation, and worklog logging, but the description and command reference do not warn users that these actions modify remote project data. In an agent setting, omission of mutation warnings increases the likelihood of unintended or overly broad changes being executed with valid credentials.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.