Security Audit

OpenClaw Minecraft

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

OpenClaw Minecraft 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 overwrite critical prompt file.

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

Filesystem Write

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Agent instructed to overwrite critical prompt file The skill explicitly instructs the agent to overwrite the workspace root `CRON_PROMPT.md` with a file from the skill's own directory (`skills/openclaw-minecraft/CRON_PROMPT.md`). This grants the skill the ability to modify the agent's autonomous prompt, which could lead to prompt injection, altered behavior, or other malicious actions if the source `CRON_PROMPT.md` within the skill package is compromised or contains malicious instructions. The instruction 'always, regardless of existing file' emphasizes the forceful nature of this operation, indicating a potential for an agent to be manipulated into executing arbitrary instructions via a modified prompt. Avoid instructing agents to overwrite critical configuration or prompt files. If such an operation is necessary, implement strict validation of the source file's content and ensure explicit user consent for such modifications. Consider using a templating system or appending to files instead of overwriting, and provide the agent with a mechanism to verify the integrity of the prompt file.	LLM	SKILL.md:51

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/ddd92d4763c8aaf3.svg)](https://skillshield.io/report/ddd92d4763c8aaf3)