ClawHub
Back to skill

Security audit

Substack Ghostwriting

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Substack ghostwriting helper, but its ghostwriting workflow encourages use of recordings and private communications without consent or data-handling safeguards.

Install only if you are comfortable with a ghostwriting workflow that may use transcripts, recordings, and private communications. Before using it, confirm consent from recorded participants and the person being ghostwritten, avoid confidential or unnecessary personal data, and do not store voice guides or source transcripts longer than needed.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

High
Confidence
97% confidence
Finding
The trigger criteria explicitly extend beyond Substack-specific tasks to 'general article/newsletter writing even if Substack isn't named explicitly,' which can cause the skill to activate outside its stated domain. That overreach may route unrelated writing requests into a workflow optimized for ghostwriting, growth, and platform-specific tactics, increasing the chance of inappropriate data gathering, unnecessary tool use, or misaligned outputs.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The guidance explicitly recommends recording calls, transcribing conversations, and using Slack/WhatsApp or internal communications as source material without any accompanying safeguards around consent, confidentiality, retention, or handling of sensitive personal and business data. In a ghostwriting skill, this creates a realistic privacy and compliance risk because users may collect or process third-party communications in ways that violate expectations, internal policy, or applicable law.

Static analysis

No suspicious patterns detected.