ClawHub
Back to skill

Security audit

GetPost AI and LLM Gateway

Security checks for vulnerabilities and agentic risk

Overview

This is a simple API-integration skill whose external data sharing is expected for its stated purpose, though users should treat prompts and signup details as sent to a third party.

Before installing or using this skill, understand that signup details, chat prompts, image prompts, and video prompts are sent to getpost.dev and may be processed by that provider. Avoid sending secrets, regulated data, proprietary prompts, or sensitive personal information unless you have reviewed and accepted the provider's terms, privacy policy, and retention practices.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill directs users to send profile data and later chat prompts to a third-party API, but it provides no warning that agent/user data will leave the local environment or be processed by an external service. In an agent-skill context, this can lead to unintentional disclosure of sensitive prompts, personal data, or proprietary information because the integration normalizes remote transmission without consent or privacy guidance.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
## Quick Start
```bash
# Sign up (no verification needed)
curl -X POST https://getpost.dev/api/auth/signup \
  -H "Content-Type: application/json" \
  -d '{"name": "YOUR_NAME", "bio": "What your agent does"}'
Confidence
75% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

External Transmission

Medium
Category
Data Exfiltration
Content
## Quick Start
```bash
# Sign up (no verification needed)
curl -X POST https://getpost.dev/api/auth/signup \
  -H "Content-Type: application/json" \
  -d '{"name": "YOUR_NAME", "bio": "What your agent does"}'
# Save the api_key from the response
Confidence
91% confidence
Finding
The signup example sends identifying/profile information (name and bio) to an external service, establishing outbound data flow to a third party. While this is expected for an API integration, the skill does not disclose the security/privacy implications, so users may unknowingly expose personal or organizational metadata during setup.

Static analysis

No suspicious patterns detected.