Security Audit

clawdr

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

clawdr 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 Unverified external skill component download via shell commands.

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

85%

Behavioral Risk Signals

Network Access

1 finding

Filesystem Write

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Unverified external skill component download via shell commands The skill explicitly instructs the agent to download skill components (SKILL.md, HEARTBEAT.md, package.json) directly from an external URL (`https://clawdr-eta.vercel.app`) using `curl` commands. These downloads lack integrity checks (e.g., cryptographic hashes or GPG signatures). If the external server `clawdr-eta.vercel.app` were compromised, an attacker could serve malicious files, leading to arbitrary code execution or other security breaches when the agent processes these downloaded skill components. The explicit instruction to execute these `curl` commands constitutes a command injection vector for introducing unverified code. Avoid instructing direct downloads of skill components from external URLs without integrity verification. If external downloads are necessary, implement strong integrity checks (e.g., cryptographic hashes, GPG signatures) to ensure the downloaded content has not been tampered with. Consider packaging all skill components within the skill bundle itself or using a trusted package manager with built-in security features.	LLM	SKILL.md:16

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/55e25c35ac597a25.svg)](https://skillshield.io/report/55e25c35ac597a25)