Security Audit

bitwarden-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 99e2a2951545

TRUSTED

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

bitwarden-automation received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Broad Access to Sensitive Password Manager.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.

Last analyzed on February 17, 2026 (commit 99e2a295). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Broad Access to Sensitive Password Manager The 'bitwarden-automation' skill, by its nature, grants an LLM agent broad access to a user's Bitwarden vault via the Rube MCP. This includes the ability to perform various Bitwarden operations (e.g., retrieve, create, update, delete entries) as indicated by the 'Core Workflow Pattern' and 'Quick Reference' sections. While this is the intended functionality of an automation skill for Bitwarden, it represents a significant security risk if the agent or the underlying Rube MCP system is compromised. A compromised agent could potentially access and exfiltrate highly sensitive credential data, leading to severe security breaches. Implement robust access controls and monitoring for the LLM agent's interactions with this skill. Ensure the Rube MCP and its Bitwarden toolkit are securely configured and regularly audited. Users should be fully aware of the extensive permissions granted to the agent when enabling this skill and only use it in highly trusted environments. If possible, configure the Bitwarden connection with the principle of least privilege, limiting the scope of operations or specific vault items the agent can access.	LLM	SKILL.md:1

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/5443c66b4b2a03b6.svg)](https://skillshield.io/report/5443c66b4b2a03b6)