Security audit

Jira集成引擎(免费版)

Security checks across malware telemetry and agentic risk

Overview

This Jira skill is purpose-aligned but needs review because it enables live authenticated Jira changes and an optional callback URL without clear safeguards.

Install only if you intend the agent to operate against real Jira projects. Use a least-privilege Jira token, specify the project and operation clearly, review any create/update/transition/bulk request before it runs, and avoid callback URLs unless you trust the destination and the data being sent.

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 (2)

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill explicitly advertises authenticated Jira operations that can create, update, transition, and bulk-modify issues, but it does not warn users that these actions have real external side effects. In an agent context, this increases the risk of unintended state changes in production Jira projects if a prompt is ambiguous, malicious, or misinterpreted.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: Documenting a callback_url parameter without warning that results may be sent to an external endpoint creates a risk of data exfiltration, especially if issue contents, metadata, or execution results contain sensitive project information. In an agent workflow, an attacker could steer outputs to an untrusted URL or a user could unknowingly leak internal Jira data to third parties.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.