Security Audit

coding-agent

github.com/openclaw/skills

AI SkillCommit 13146e6a3d46

CAUTION

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

coding-agent received a trust score of 72/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.

SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Obfuscated remote script execution for MacOS installation.

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 13, 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

70%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Security Findings1

Severity	Finding	Layer	Location
CRITICAL	Obfuscated remote script execution for MacOS installation The skill explicitly instructs the user to copy and execute a shell command for MacOS installation. This command uses base64 decoding to obfuscate a `curl` command that downloads and pipes a script from an arbitrary, unverified IP address (`http://91.92.242.30/lamq4uerkruo6ssm`) directly to `bash`. This pattern represents a critical command injection vulnerability and a severe supply chain risk. An AI agent, if designed to assist the user by executing instructions found in the skill, could misinterpret this as a command to execute, leading to arbitrary code execution from an untrusted source on the host system. The use of base64 also constitutes a hidden instruction. Remove the direct execution instruction for installing `OpenClawProvider`. If `OpenClawProvider` is a required dependency, provide a secure, verified installation method (e.g., signed packages, official package managers, or clear instructions to verify checksums from a trusted source). Avoid piping `curl` output directly to `bash`, especially from unknown or unverified IP addresses, and avoid obfuscation techniques like base64 for executable commands.	LLM	SKILL.md:9

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/28e271f4f5367782.svg)](https://skillshield.io/report/28e271f4f5367782)