ClawHub
Back to skill

Security audit

掘金工具专业版

Security checks for vulnerabilities and agentic risk

Overview

This skill is aimed at Juejin publishing and analytics, but it combines broad activation wording with multi-account posting authority and session-cookie handling that users should review carefully.

Install only if you intend to automate Juejin team publishing. Keep cookie files encrypted and access-limited, do not paste cookie values into prompts or logs, use draft mode by default, and require explicit human approval before any scheduled or public multi-account posting.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger condition is broad enough to activate on generic requests for data analysis, reporting, or visualization, even when the user did not intend to use this Juejin automation skill. In context, this is more dangerous because the skill advertises exec/write capabilities and batch publishing behavior, so accidental invocation could lead to unintended account or content operations.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill instructs users to configure and centrally store multiple account cookies, which are sensitive session credentials, without prominent upfront warnings about theft, misuse, scope of access, and safe handling. In this skill's context, the risk is elevated because those cookies grant multi-account publishing capability, so exposure could enable unauthorized posting, account takeover of active sessions, or cross-account abuse at scale.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill promotes batch and scheduled publishing across multiple accounts without an upfront warning that it can perform large-scale account actions if misconfigured or accidentally triggered. This is especially concerning here because the skill includes exec/write tooling and matrix-account workflows, increasing the blast radius of mistakes or abuse into mass posting, spam, policy violations, or reputational damage across many accounts.

Static analysis

No suspicious patterns detected.