Security Audit

clawdbot-workspace-template-review

github.com/openclaw/skills

AI SkillCommit 13146e6a3d46

TRUSTED

Scanned 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

clawdbot-workspace-template-review 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 Potential Command Injection via Unsanitized Paths.

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 14, 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

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Potential Command Injection via Unsanitized Paths The skill instructs the LLM to execute shell commands (`ls`, `sed`, `diff`) using paths that are either directly provided by the user (`<workspace>`) or derived from external command output (`<clawdbot-root>`). If the LLM directly interpolates these paths into shell commands without proper sanitization or escaping, a malicious user could inject arbitrary shell commands by crafting a path containing shell metacharacters (e.g., `;`, `\|`, `&`, `$(...)`). This could lead to unauthorized file access, data exfiltration, or arbitrary code execution on the host system. The LLM must be explicitly instructed to sanitize or properly escape all user-provided or externally derived path variables (e.g., `<workspace>`, `<clawdbot-root>`) before incorporating them into shell commands. Ideally, the LLM should use a secure, parameterized method for executing commands that prevents shell injection, or at minimum, ensure all special shell characters are escaped. For example, paths should be quoted and escaped to prevent interpretation as commands or arguments.	LLM	SKILL.md:34

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/ba9c378119331495.svg)](https://skillshield.io/report/ba9c378119331495)