OpenClaw GEO Content Ops

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 8:47 AM UTC
• Version: 0.1.0

Overview

This skill is a disclosed content-operations guide and does not include hidden execution, credential access, or background persistence.

Installers should understand that the skill can help coordinate publishing workflows and publication evidence. Before using it with separate tools that can post, deploy, update, or unpublish live content, verify the target, credentials, approval path, and receipts.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Rogue Agent: Self-Modification, Session Persistence
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (14)

Intent-Code Divergence

Medium

• Category: Not specified by scanner
• Confidence: 84% confidence

Finding

The documentation explicitly states '这个 repo 是运营层，不替代写作 skill，也不替代发布 workflow', implying it is not itself a publishing workflow. However, elsewhere the same README says the skill 'supports ClawLite blog, WordPress REST, static GEO site, X posts, Feishu docs' as publication targets and cites 'local publish 与 remote distribution 分离' as a borrowed capability, which creates an intent-level contradiction about whether the skill only plans/audits publishing or also performs distribution.

Content

No source excerpt is available for this finding.

Session Persistence

Medium

• Category: Rogue Agent
• Confidence: 60% confidence

Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · README.md (reported line 109)May include surrounding context.

安装为 Codex Skill

bash

mkdir -p ~/.codex/skills
git clone https://github.com/X-RayLuan/openclaw-geo-content-ops.git ~/.codex/skills/openclaw-geo-content-ops

Session Persistence

Medium

• Category: Rogue Agent
• Confidence: 60% confidence

Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · docs/readme/README_en.md (reported line 69)May include surrounding context.

Quick Start

bash

mkdir -p ~/.codex/skills
git clone https://github.com/X-RayLuan/openclaw-geo-content-ops.git ~/.codex/skills/openclaw-geo-content-ops

Skill Enumeration

Medium

• Category: Agent Snooping
• Confidence: 85% confidence

Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · README.md (reported line 109)May include surrounding context.

Quick Start

bash

mkdir -p ~/.codex/skills
git clone https://github.com/X-RayLuan/openclaw-geo-content-ops.git ~/.codex/skills/openclaw-geo-content-ops

Skill Enumeration

Medium

• Category: Agent Snooping
• Confidence: 85% confidence

Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · docs/readme/README_en.md (reported line 69)May include surrounding context.

Quick Start

bash

mkdir -p ~/.codex/skills
git clone https://github.com/X-RayLuan/openclaw-geo-content-ops.git ~/.codex/skills/openclaw-geo-content-ops

Skill Enumeration

Medium

• Category: Agent Snooping
• Confidence: 85% confidence

Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · docs/readme/README_es.md (reported line 58)May include surrounding context.

Quick Start

bash

mkdir -p ~/.codex/skills
git clone https://github.com/X-RayLuan/openclaw-geo-content-ops.git ~/.codex/skills/openclaw-geo-content-ops

Skill Enumeration

Medium

• Category: Agent Snooping
• Confidence: 85% confidence

Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · docs/readme/README_ja.md (reported line 58)May include surrounding context.

Quick Start

bash

mkdir -p ~/.codex/skills
git clone https://github.com/X-RayLuan/openclaw-geo-content-ops.git ~/.codex/skills/openclaw-geo-content-ops

Skill Enumeration

Medium

• Category: Agent Snooping
• Confidence: 85% confidence

Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · docs/readme/README_pt_BR.md (reported line 58)May include surrounding context.

Quick Start

bash

mkdir -p ~/.codex/skills
git clone https://github.com/X-RayLuan/openclaw-geo-content-ops.git ~/.codex/skills/openclaw-geo-content-ops

Skill Enumeration

Medium

• Category: Agent Snooping
• Confidence: 85% confidence

Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · docs/readme/README_ru.md (reported line 58)May include surrounding context.

Quick Start

bash

mkdir -p ~/.codex/skills
git clone https://github.com/X-RayLuan/openclaw-geo-content-ops.git ~/.codex/skills/openclaw-geo-content-ops

Session Persistence

Medium

• Category: Rogue Agent
• Confidence: 60% confidence

Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · docs/readme/README_es.md (reported line 58)May include surrounding context.

Quick Start

bash

mkdir -p ~/.codex/skills
git clone https://github.com/X-RayLuan/openclaw-geo-content-ops.git ~/.codex/skills/openclaw-geo-content-ops

Session Persistence

Medium

• Category: Rogue Agent
• Confidence: 60% confidence

Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · docs/readme/README_ja.md (reported line 58)May include surrounding context.

Quick Start

bash

mkdir -p ~/.codex/skills
git clone https://github.com/X-RayLuan/openclaw-geo-content-ops.git ~/.codex/skills/openclaw-geo-content-ops

Session Persistence

Medium

• Category: Rogue Agent
• Confidence: 60% confidence

Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · docs/readme/README_pt_BR.md (reported line 58)May include surrounding context.

Quick Start

bash

mkdir -p ~/.codex/skills
git clone https://github.com/X-RayLuan/openclaw-geo-content-ops.git ~/.codex/skills/openclaw-geo-content-ops

Session Persistence

Medium

• Category: Rogue Agent
• Confidence: 60% confidence

Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · docs/readme/README_ru.md (reported line 58)May include surrounding context.

Quick Start

bash

mkdir -p ~/.codex/skills
git clone https://github.com/X-RayLuan/openclaw-geo-content-ops.git ~/.codex/skills/openclaw-geo-content-ops

Missing User Warnings

Low

• Category: Not specified by scanner
• Confidence: 78% confidence

Finding

This markdown file applies to SQP-2, which requires warnings when described behaviors could affect user data, privacy, or system integrity. The skill description includes publication targets and receipts for publication/deploy/live QA, but does not warn users that using the skill may publish or modify live content or external systems.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.