Back to skill

Security audit

保险产品解析

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrowly scoped insurance product lookup tool that calls a disclosed product-detail API and does not show hidden persistence, credential access, destructive behavior, or privilege escalation.

Before installing, confirm that you are comfortable with product identifiers being sent to the disclosed hongdibaobei.com API and be cautious when product names have multiple versions. Ask the agent to list or confirm matches instead of relying on the first automatic match, especially for insurance decisions.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
95% confidence
Finding

The trigger condition is broadly defined as any user asking for product details or configurations, which can cause the skill to activate in contexts where the user did not explicitly intend an API-backed insurance product lookup. In an agent setting, ambiguous activation increases the chance of unintended data retrieval, wrong tool use, or acting on partial product-name matches without sufficient confirmation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill automatically selects the first matching product when multiple products share a similar name, but this behavior is not surfaced as a prominent warning before execution. That can lead to users receiving details for the wrong insurance plan, creating a risk of misinformation or downstream decisions based on an unintended product version.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This code file contains user-facing natural language in the module docstring and command-line help text exclusively in Chinese, which effectively forces a specific language for users. The file does not offer an alternative language, locale selection, or state that the skill is intentionally region-specific.

Content

No source excerpt is available for this finding.