ClawHub
Back to skill

Security audit

Bilibili Messager | B站私信助手

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Bilibili private-message helper that uses a logged-in dedicated browser profile; users should be careful to confirm any outgoing message explicitly.

Install only if you are comfortable letting the agent read selected Bilibili private-message content and send DMs from the logged-in account. Use a dedicated openclaw browser profile, verify the account before use, and require an exact confirmation that includes the recipient and message before allowing any send or reply.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The skill allows broad confirmation phrases such as '好', '确认', '发', and '发吧' to authorize an irreversible outbound DM. In a conversational system, these phrases can easily appear ambiguously in normal dialogue or be elicited by prompt manipulation, creating a real risk of unintended message sending from the logged-in account.

Static analysis

No suspicious patterns detected.