Back to skill

Security audit

ClawHub Publishing Workflow

Security checks for vulnerabilities and agentic risk

Overview

This is a registry-management skill whose sensitive actions are visible and aligned with publishing and managing OpenClaw skills.

Before installing, treat this as a publishing and registry-management helper: only run publish, sync, uninstall, delete, hide, or unhide after confirming the target skill, account, and registry, and protect the local ClawHub token with appropriate filesystem permissions.

Vulnerability Patterns
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 69)May include surrounding context.

md
- ✅ `SKILL.md` exists with Name and Description

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Section headings such as "MISIÓN" and "CONFIGURACIÓN" establish a Spanish-only presentation, while the document does not state that Spanish is required or provide an opt-in or alternative language. This is a natural-language locale policy issue because the skill effectively forces a specific language without user choice or justification.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown file documents deletion, hiding, unhiding, and uninstall operations, which can affect published skills and user environment state, but it does not include any cautionary warning about reversibility, permissions, or consequences. Under the markdown-file criteria for missing user warnings, user-facing documentation should warn when actions may affect data or system integrity.

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 · SKILL.md (reported line 189)May include surrounding context.

bash
# Full workflow automation
./publish-to-clawhub.sh validate <path>   # Check structure
./publish-to-clawhub.sh package <path>    # Create tarball
./publish-to-clawhub.sh publish <path>    # Upload to registry
./publish-to-clawhub.sh sync <dir>        # Batch publish

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

The file explicitly documents local paths including ~/.config/clawhub/token, revealing the location of an authentication token and the broader local skill/workspace layout. While not a secret disclosure by itself, this materially aids follow-on attacks, social engineering, or malicious local tooling by telling an attacker exactly where to look for sensitive session material.

Content

Scanner excerpt · SKILL.md (reported line 198)May include surrounding context.

md
## 📁 FILES

- `~/.openclaw/skills/clawhub/SKILL.md` (this file)
- `~/.openclaw/workspace/scripts/publish-to-clawhub.sh` (publishing automation)
- `~/.openclaw/workspace/docs/clawhub-publishing-guide.md` (documentation)
- `~/.config/clawhub/token` (authentication token)