Bearer

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Bearer integration, but it gives an agent broad authenticated API access, including write and delete requests, without clear confirmation or scoping safeguards.

Install only if you are comfortable letting Membrane-mediated agent workflows access your Bearer account. Use the least-privilege account or workspace available, consider pinning or verifying the Membrane CLI package, and require explicit approval before the agent creates, updates, or deletes Bearer data.

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: 91% confidence
Finding: The skill exposes a generic proxy request mechanism to an external API without an explicit warning about data egress, which can encourage agents to send arbitrary user or workspace data off-platform. In an agent setting, this is risky because the proxy can bypass the safer, schema-discovered action flow and enable broad external operations with less user awareness.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal