Backlog

Security checks across malware telemetry and agentic risk

Overview

This is a legitimate Backlog integration, but it gives an agent broad authenticated ability to change or delete project data without clear confirmation safeguards.

Install only if you trust Membrane and the npm CLI package. Use the least-privileged Backlog account available, review the permissions granted, and require the agent to show the exact action, target issue/project, and payload before any create, update, delete, comment, or raw API request runs.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
88% confidence
Finding
The skill advertises destructive capabilities like deleting issues alongside routine actions without any warning, confirmation requirement, or guidance to obtain explicit user consent. In an agent setting, this increases the chance that a loosely instructed model could invoke destructive operations accidentally or without adequate user awareness, leading to integrity loss in project data.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal