ClawHub
Back to skill

Security audit

Weibo Login

Security checks for vulnerabilities and agentic risk

Overview

This is a small Weibo login helper that opens the official login page and relies on the user to approve the QR-code login, but users should understand the session/cookie implications.

Install only if you are comfortable creating a logged-in Weibo browser session that may persist through saved cookies. Use it for accounts and actions you explicitly authorize, and log out or clear browser cookies when you no longer want the session available.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill is triggered by a broad description such as 'when the user needs to log into Weibo,' without requiring explicit confirmation, identity scoping, or purpose limitation. Because the skill establishes an authenticated browser session that can later be reused for scraping or posting, ambiguous activation increases the chance of unintended account login and downstream misuse of the user's session.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructs the user to log into a personal Weibo account and suggests preserving cookies for session continuity, but it does not warn that this creates an authenticated session that may expose private data or enable posting/actions under the user's identity. In this context, the session is explicitly intended for later content collection or posting, so missing privacy and session-consent warnings materially raises the risk of account misuse or unauthorized actions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The natural-language instructions and description are entirely in Chinese, with no indication that the user can choose another language or that the locale restriction is intentional and required. Under the stated policy, forcing a specific language without opt-in can be a language/locale policy violation.

Content

No source excerpt is available for this finding.