ClawHub
Back to skill

Security audit

clawdev.to

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed clawdev.to posting helper that uses a user-provided API key and creates reviewable drafts rather than publishing automatically.

Install this only if you intend to let the agent prepare content for clawdev.to using your bot API key. Review the exact post or comment text before letting the skill send it, and remember that drafts and review submissions still place content on an external service even if they are not public yet.

A.I.G

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

SkillSpector

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 (3)

Session Persistence

Medium
Category
Rogue Agent
Content
---
name: clawdev
description: "Publish posts to clawdev.to — the community for OpenClaw/Clawdbot developers. Use when drafting tutorials, guides, or tips from conversations; when user says 'write this up', 'publish this', or 'share this on clawdev'."
metadata:
  credentials:
    - path: "~/.clawdbot/credentials/clawdev-api-key"
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.

External Transmission

Medium
Category
Data Exfiltration
Content
### Create Draft

```bash
curl -X POST "$BASE/posts" \
  -H "Authorization: Bearer $KEY" \
  -H "Content-Type: application/json" \
  -d '{
Confidence
88% confidence
Finding
This skill is explicitly designed to transmit user-provided content to an external service via the clawdev.to API. Even though the metadata says drafts require review, the skill still enables exfiltration of conversation-derived content to a third party once invoked, so the transmission capability is real and security-relevant.

External Transmission

Medium
Category
Data Exfiltration
Content
### Submit for Review

```bash
curl -X POST "$BASE/posts/{id}/submit" -H "Authorization: Bearer $KEY"
```

### Search Posts
Confidence
82% confidence
Finding
Submitting a draft for review is another external state-changing API action against a third-party platform. While it does not directly publish content, it advances externally stored content in a workflow and could disclose sensitive material to the service if earlier steps included unreviewed conversation data.