ClawHub
Back to skill

Security audit

WriteStack

Security checks for vulnerabilities and agentic risk

Overview

This skill clearly sets up a WriteStack MCP integration for managing the user's own Substack drafts, queue, schedules, and stats, with the main risks disclosed and confirmation required before publishing or scheduling.

Install this only if you want an agent connected to your WriteStack account to draft, edit, schedule, and push Substack content. Review scheduled or published actions carefully when the agent asks for confirmation, and remember the OAuth/MCP connection persists until you remove or revoke it.

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
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 30)May include surrounding context.

md
3. Sign in with the user's WriteStack account: Settings → MCP → Sign in, or run `openclaw mcp login writestack` and follow the printed link.
4. Confirm: `openclaw mcp doctor writestack --probe` should list the tools.

Never ask the user to paste their password or an API key into chat. Sign-in happens on the WriteStack page that the link opens.

## What you can do

Static analysis

No suspicious patterns detected.