Security Audit

Vincent - A wallet for agents

github.com/openclaw/skills

AI SkillCommit 13146e6a3d46

TRUSTED

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

Vincent - A wallet for agents 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 Agent instructed to store and retrieve API keys from local filesystem.

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 12, 2026 (commit 13146e6a). 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

Network Access

1 finding

Filesystem Write

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Agent instructed to store and retrieve API keys from local filesystem The skill documentation explicitly instructs the agent to store generated API keys in local files (`~/.openclaw/credentials/agentwallet/<API_KEY_ID>.json` or `agentwallet/<API_KEY_ID>.json`) and to retrieve them for subsequent API calls. This implies the agent will have filesystem read/write access. If the agent's filesystem access is not strictly confined to these specific files, or if its output is not properly sanitized, a malicious prompt could instruct the agent to read these credential files and exfiltrate their contents, or other sensitive files on the system. Implement strict sandboxing for agent filesystem access, limiting it only to necessary directories and file operations. Ensure that any agent output is thoroughly sanitized to prevent accidental or malicious exfiltration of file contents. Consider using secure credential stores (e.g., OS-level keychains, environment variables, or dedicated secrets management services) instead of plain files for API keys, or ensure the agent's environment variables are not easily accessible.	LLM	SKILL.md:160

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/06ae923f7d9a5ae0.svg)](https://skillshield.io/report/06ae923f7d9a5ae0)