ClawHub
Back to skill

Security audit

Social Media Manager

Security checks for vulnerabilities and agentic risk

Overview

The skill is not deceptive, but it can post or schedule content across connected social accounts through Postiz with broad scope and weak approval and credential-handling guidance.

Review this skill carefully before installing. Use a dedicated least-privilege Postiz API key, avoid putting the key directly in visible command lines, and require explicit confirmation of the exact platforms, accounts, media, caption, and timing before any live post or scheduled post. Prefer draft-only operation until you have verified the generated content and destinations.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:50
Finding

Postiz API Credential Exposure Through Command-Line Arguments

Content
View full analysis
Remediation
View remediation

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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill is designed to publish content across multiple connected social media accounts through a third-party API, but it does not warn about the privacy, reputational, and account-security risks of sending generated media and captions to an external service. In this context, omission of those warnings is meaningful because the skill encourages broad cross-posting and scheduling across 'any platform,' increasing the blast radius of mistakes, unauthorized posts, or sensitive-content disclosure.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
80% confidence
Finding

Referencing a specific third-party API endpoint is not inherently unsafe, but here it is part of an operational workflow whose purpose is to transmit user-generated content and perform actions on external social accounts. In the context of an automation skill that can target many platforms, this external dependency materially increases the risk of unintended disclosure, unwanted posting, and account-impacting actions.

Content

Scanner excerpt · SKILL.md (reported line 39)May include surrounding context.

md
Postiz acts as the universal publishing layer. One API handles all connected platforms.

### Configuration
- **API URL**: `https://api.postiz.com/public/v1`
- **Auth Header**: `Authorization: <API_KEY>` (No Bearer prefix).
- **Media Upload**: `POST /upload` first to get `id` and `path`.
- **Posting Method**: Use `UPLOAD` (Draft) for multi-image content. `DIRECT_POST` works for single-image/text posts.

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

The skill includes concrete commands for uploading media, creating posts, and enumerating connected integrations against an external API using an authorization key. This creates a real external-transmission risk because user content and account linkage data may be transmitted to a third party, and the integration-listing capability can expose all connected publishing destinations if misused or invoked without sufficient user awareness.

Content

Scanner excerpt · SKILL.md (reported line 50)May include surrounding context.

md
- Settings level: Platform-specific settings (e.g., `__type: "tiktok"`, `__type: "instagram"`, etc.).

### Technical Specs
- **Upload Media**: `curl -X POST {API_URL}/upload -H "Authorization: {KEY}" -F "file=@path/to/file"`
- **Create Post**: `curl -X POST {API_URL}/posts -H "Authorization: {KEY}" -H "Content-Type: application/json" -d '{...}'`
- **List Integrations**: `curl {API_URL}/integrations -H "Authorization: {KEY}"` — use this to discover connected platforms and their integration IDs.

Static analysis

No suspicious patterns detected.