ClawHub
Back to skill

Security audit

juejin-pins-publish

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says, but it can publish public Juejin posts from a logged-in browser without a final confirmation step.

Install only if you are comfortable with the agent using your logged-in Juejin browser session to publish posts. Review the content, selected club/topic, links, code, and images yourself before allowing the final publish action; the skill does not enforce that confirmation on its own.

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

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger description is broad enough to activate on ordinary requests about posting to Juejin, which increases the chance the skill runs in situations where the user did not intend this exact automation. Because the skill performs a public posting action, ambiguous activation boundaries can lead to unintended publication of user-provided content to a live account.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The workflow ends with clicking the publish button without requiring a final user warning or confirmation, even though this creates a public post on the user's authenticated Juejin account. In this context, omission of a final confirmation is especially risky because the action is irreversible in effect and may expose private, mistaken, or attacker-influenced content to a public audience.

Static analysis

No suspicious patterns detected.