Jazzhr

Security checks across malware telemetry and agentic risk

Overview

This JazzHR skill is a coherent integration, but it gives an agent broad authenticated access to sensitive hiring data, including write and delete API calls, without clear confirmation safeguards.

Install only if you trust Membrane and intend to connect it to JazzHR. Use a least-privilege JazzHR account where possible, review the Membrane CLI package/version before installing, and require explicit human approval before the agent creates, updates, or deletes applicants, jobs, users, or other JazzHR records.

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: 89% confidence
Finding: The skill explicitly documents raw proxy access with mutating HTTP methods like POST, PUT, PATCH, and DELETE, but does not instruct the agent to obtain explicit confirmation before performing state-changing operations. In an agent setting, this increases the chance of unintended writes, deletions, or workflow changes in a live HR system containing sensitive recruiting data.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal