Back to skill

Security audit

Insurance Ai News

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed bilingual insurance AI news brief generator that searches public news and syncs the finished report to Feishu, with no bundled executable code or hidden persistence found.

Install this if you want an automated bilingual insurance AI news brief that can create and append Feishu documents. Before enabling scheduled use, confirm which Feishu account or workspace the document tool will write to and whether automatic daily publishing is desired.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly states that generated reports will be synchronized to a Feishu document, but it does not require user notice, consent, or any data-handling warning before sending content to an external service. This creates a real privacy and data-governance risk because user prompts, curated content, or derived summaries may be transmitted off-platform automatically, especially under scheduled execution.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The document marks the format rules as mandatory and requires all content to be presented in Chinese and English, with English first. This imposes a language/locale behavior by default without documenting user opt-in or offering an alternative, which fits the language-policy violation category.

Content

No source excerpt is available for this finding.