Back to skill

Security audit

浏览器办事流程助手

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language browser-task planning and validation helper with clear safeguards around credentials, payments, posting, deletion, and other sensitive actions.

Install only if you are comfortable with a Chinese-language workflow helper and any optional AI-HIVE/MCP connection. Keep login on official pages, do not paste passwords or tokens into chat, and require explicit review before uploads, payments, messages, deletion, business-system writes, or public posting.

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
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (6)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill advertises browser-agent planning and web task assistance, but the content shown primarily directs reading local references and running an offline checker. This mismatch is dangerous because users and integrators may authorize the skill expecting one behavior while it actually performs different local/backend-style actions, undermining informed consent, review accuracy, and security assumptions about what the skill can do.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding

The skill references local files and scripts such as assets/, references/, and scripts/check_result.py, but it does not declare any explicit tool scope or permissions boundary. Missing scope declarations can cause the runtime to grant broader file-read capability than reviewers or users expect, increasing the risk of unintended local file access or capability confusion.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest description and main skill content are entirely written in Chinese and present the skill as operating in Chinese by default, with no indication that users may choose another language. This can violate language/locale policy when a skill imposes a language without user opt-in or clear region-specific justification.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The activation and default prompt are broadly worded and can cause the skill to be invoked for loosely related browser or task-automation requests without clear gating. In a browser-action skill, overbroad triggering increases the chance of the agent collecting sensitive inputs, proposing high-risk web actions, or being used outside its intended scope without explicit user confirmation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

All user-facing manifest text is presented only in Chinese, and there is no indication that the user can select another language or that the skill is intentionally limited to a Chinese-language context. This may violate language/locale policy where user opt-in or documented locale restriction is required.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The natural-language note is written entirely in Chinese, which imposes a specific language on users of this intake template. There is no indication that the skill is region-specific or that users may choose another language, so this can violate language/locale policy expectations.

Content

No source excerpt is available for this finding.