ClawHub
Back to skill

Security audit

SocialFaktory: Social Media Scheduler and Video Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed SocialFaktory integration for drafting, generating, scheduling, and publishing social posts with explicit OAuth consent and user approval steps for spending credits or publishing.

Before installing, confirm you trust SocialFaktory with the selected brand and channels, choose the narrowest OAuth permissions you need, set a monthly credit cap and expiry, and review drafts before allowing posts to be queued or published.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
expiry. If the browser cannot reach the callback, run the `--code` command that `login` prints.
The tools are available on the next turn.

The sign-in is OAuth in the user's browser. Never ask the user to paste a password or token into
the chat.

### Fallback: mcporter
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.

Static analysis

No suspicious patterns detected.