Back to skill

Security audit

上市公司同业对比分析报告

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent report-writing workflow for public listed-company comparison analysis, with no hidden code or persistence.

Installers should expect this skill to call financial-data and news/search tools and to return a generated Markdown report. Review outputs carefully because financial analysis may be time-sensitive and should not be treated as investment advice.

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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest description is entirely in Chinese and states when this skill should be used for user requests, implying the skill is designed to operate in Chinese by default. There is no indication that users may choose another language or that the Chinese-only constraint is required for a region-specific compliance reason.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill instructs the agent to generate a file and automatically return it via deliver_attachments, but it does not require explicit user consent or even a clear user-visible notice before creating and transmitting an artifact. This can lead to unexpected file creation/exfiltration behavior, especially if the user expected only an inline response or if generated content includes sensitive retrieved data.

Content

No source excerpt is available for this finding.