Beacon

Security checks across malware telemetry and agentic risk

Overview

This appears to be a normal Membrane-based app integration skill with expected authenticated API access, but users should be careful with raw write or delete requests.

Install only if you trust Membrane and intend to let the agent operate on this service account. Prefer discovered pre-built actions first, review any raw POST/PUT/PATCH/DELETE request before it runs, and use an account with the least privileges needed.

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 requests with mutating HTTP verbs like POST, PUT, PATCH, and DELETE, but does not warn that these operations can alter or remove production data. In an agent context, this increases the risk of unintended destructive actions because the model is given a generic mechanism to perform state-changing API calls without requiring confirmation or safety guidance.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal