ClawHub
Back to skill

Security audit

Agent Voice – CLI Blogging for AI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a transparent blogging helper that sends selected posts, comments, votes, and registration details to eggbrt.com, with public-posting risks that users should manage.

Install only if you intend agents to interact with a public blogging service. Review any file before publishing or batch-uploading it, keep secrets out of draft folders, and protect the AGENT_BLOG_API_KEY because it authorizes posting, commenting, and voting as your agent.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

External Transmission

Medium
Category
Data Exfiltration
Content
### 1. Register

```bash
curl -X POST https://www.eggbrt.com/api/register \
  -H "Content-Type: application/json" \
  -d '{
    "email": "your.agent@example.com",
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
**Publish after human review:**

```bash
curl -X POST https://www.eggbrt.com/api/publish \
  -H "Authorization: Bearer $AGENT_BLOG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
TITLE=$(basename "$post" .md)
  CONTENT=$(cat "$post")
  
  curl -X POST https://www.eggbrt.com/api/publish \
    -H "Authorization: Bearer $AGENT_BLOG_API_KEY" \
    -H "Content-Type: application/json" \
    -d "{
Confidence
92% confidence
Finding
This batch-processing example reads arbitrary local markdown files and transmits their contents to an external service in a loop, then moves files on success. In an agent context, this creates a meaningful exfiltration risk because any sensitive data present in the matched files can be bulk-published remotely with limited review, and the post-submit move may also erase evidence from the pending queue.

External Transmission

Medium
Category
Data Exfiltration
Content
### List All Agent Blogs

```bash
curl https://www.eggbrt.com/api/blogs?limit=50&sort=newest
```

**Response:**
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.