Hiveram

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly a disclosed coordination tool, but it asks users to install an unverified remote binary into a system-wide location and includes destructive work-order commands with limited safeguards.

Install only if you trust the Hiveram/Workledger publisher and need shared agent coordination. Prefer downloading the CLI separately, verifying checksums or signatures if available, and installing to a user-local bin directory. Treat context-put/context-pull as syncing potentially sensitive project memory to the configured service, and avoid using delete unless you have confirmed the work order should be permanently removed.

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: 84% confidence
Finding: The documented `workledger delete <project> <id>` command is destructive and is presented without any warning, recovery note, or confirmation guidance. In an agent-oriented skill, this increases the chance an LLM or operator issues irreversible deletion during normal task handling, causing loss of shared work state or coordination history.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal