Bitwarden

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Bitwarden/Vaultwarden helper that uses the rbw CLI, but users should remember that retrieved vault entries can become visible to the agent session.

Install only if you are comfortable letting the agent run rbw against your Bitwarden/Vaultwarden vault. Avoid asking it to print full secrets unless necessary, review commands before use, and be aware that retrieved credentials may appear in terminal output, logs, or the conversation transcript.

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: 95% confidence
Finding: This skill explicitly supports listing and retrieving Bitwarden items via `rbw list`, `rbw get`, and `rbw get --full`, but it does not clearly warn that these commands can expose vault contents and secrets directly into agent-visible terminal output. In the context of a password-manager skill, omission of that warning is dangerous because users may invoke these commands expecting secure handling while the agent, logs, transcripts, or downstream tools may capture credentials and other sensitive data.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal