ClawHub
Back to skill

Security audit

OpenClaw SEO-GEO Workflow

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent SEO publishing runbook, but it delegates important work to unaudited local scripts and can trigger production-impacting deploy and diagnostic access.

Install only if you trust and control the external /Users/m1/.openclaw/workspace scripts and deployment environment. Before using live deploy or main-site write paths, verify the scripts, dependency versions, credentials, and deployment target, and avoid broad log or messaging-session inspection unless explicitly needed and sanitized.

A.I.G

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Findings (3)

T08 · Insecure Dependencies

Error
Location
SKILL.md:20
Finding

Execution of Mutable Scripts Outside the Audited Skill Package

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Error
Location
SKILL.md:68
Finding

Unpinned npm Package Execution in the Production Deployment Path

Content
View full analysis
Remediation
View remediation

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
SKILL.md:193
Finding

Overly Broad Access to Logs and Active Messaging Sessions

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Session Persistence

Medium
Category
Rogue Agent
Confidence
75% 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 · SKILL.md (reported line 204)May include surrounding context.

md
Check:

- OpenClaw logs: `/Users/m1/.openclaw/logs/*.log`
- LaunchAgents: `launchd/ai.openclaw.daily-seo-geo-blog-factory.plist`
- runner receipt freshness under `mission-control/data/runner/`
- active OpenClaw sessions if the task was triggered through Feishu/Discord/Telegram

Static analysis

No suspicious patterns detected.