Back to skill

Security audit

skill1

Security checks for vulnerabilities and agentic risk

Overview

This skill is a transparent public-data research helper for big-tech company analysis and does not show hidden execution, persistence, credential access, or destructive behavior.

Before installing, note that reports may default to Chinese section headings and should be treated as research context, not personalized investment advice. The skill relies on fresh public financial data, so users should verify dates and sources before acting on any analysis.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file requires the model to output specific Chinese text such as "未找到公开最新数据," and later mandates Chinese section headings as part of the report structure. This imposes a language choice on users regardless of their preferred locale, and the skill does not state that language should follow user preference or provide an opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The output structure requires fixed Chinese headings like "核心摘要," "商业模式," and "数据来源与日期" for every report. Because the skill also supports English prompts, this is a forced locale constraint rather than a documented region-specific requirement or user-selected option.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The report template is written as the exact output skeleton and begins with Chinese headings and field labels, indicating the skill expects output in Chinese by default. This imposes a specific language without offering user opt-in or explaining a region-specific requirement, which is a natural-language policy violation under the locale rule.

Content

No source excerpt is available for this finding.