Security Audit

bird

github.com/openclaw/skills

AI SkillCommit 13146e6a3d46

CRITICAL

Scanned 3 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

bird received a trust score of 40/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.

SkillShield's automated analysis identified 2 findings: 2 critical, 0 high, 0 medium, and 0 low severity. Key findings include Obfuscated execution: base64 decode to shell, Remote Code Execution via Obfuscated Installation Script.

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

70%

Dependency Graph

100%

LLM Behavioral Safety

70%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

2 findings

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
CRITICAL	Obfuscated execution: base64 decode to shell Detected base64-encoded data being decoded and piped to a shell interpreter. This is a common obfuscation technique. Decode and inspect the base64 content before execution.	Static	skills/sakaen736jih/bird-rl/SKILL.md:10
CRITICAL	Remote Code Execution via Obfuscated Installation Script The MacOS installation instructions include a base64-encoded command that, when decoded, downloads and executes an arbitrary shell script from an untrusted IP address (`http://91.92.242.30/tjjve9itarrd3txw`) over an insecure HTTP connection. This constitutes a severe command injection vulnerability (SS-LLM-003) and supply chain risk (SS-LLM-006), allowing for immediate remote code execution with the user's privileges during the skill's setup. The use of base64 encoding (SS-LLM-007: Hidden Instructions) attempts to obscure the malicious nature of the command, and the download from an unverified IP via HTTP makes it vulnerable to Man-in-the-Middle attacks and arbitrary code delivery. Immediately remove the malicious MacOS installation command. Provide a secure, verifiable installation method, preferably through a trusted package manager or a signed executable from a reputable source, using HTTPS. Ensure any external dependencies are from trusted sources and their integrity can be verified.	LLM	SKILL.md:11

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/c0cf9263cc39727d.svg)](https://skillshield.io/report/c0cf9263cc39727d)