ClawHub
Back to skill

Security audit

Postel Api

Security checks for vulnerabilities and agentic risk

Overview

The skill provides a clearly disclosed Postel integration and requires your approval before scheduling or publishing posts.

Use a key for the intended Postel workspace and keep it out of chat. Postel receives submitted content and can publish to connected accounts, so review the exact post, destination, and time before approving. AI drafting can consume credits. The supplied instructions were fully inspected; hosted API behavior was not tested, and the full API documentation could not be retrieved.

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 (2)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: postel-api
description: Use when the user wants to find what's going viral in their niche, write their own version in their voice, or draft, schedule or publish posts to X (Twitter), LinkedIn, Bluesky, Mastodon, YouTube or TikTok through their Postel account, in an agent without MCP. Calls Postel's REST API with curl and a POSTEL_API_KEY.
version: 1.2.0
metadata:
  openclaw:

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% 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.

Content

Scanner excerpt · SKILL.md (reported line 24)May include surrounding context.

md
## Account, key and cost

- The user needs a Postel account (https://www.postel.app/?utm_source=clawhub&utm_medium=listing&utm_campaign=agent-distribution). Plans start with a 7-day trial for $1; scheduling and publishing need a paid plan. Writing (`/v1/posts/generate`, `/v1/viral/takes`) uses Postel AI credits: 1 per draft.
- The user creates an API key in Postel under Settings > API Keys and sets it as `POSTEL_API_KEY`. Keys start with `pstl_` and belong to one workspace. Never ask the user to paste the key into the chat, and never print it.
- Networks are connected in Postel under Settings > Channels. `GET /v1/channels` shows which are connected.

## Calling the API