Back to skill

Security audit

US Stock Valuation Model - Value Investing Framework / 美股估值模型-价值投资框架

Security checks for vulnerabilities and agentic risk

Overview

This is a small, disclosed financial-rule evaluator that reads local JSON input and writes local result files, with no evidence of hidden access, persistence, or exfiltration.

Install only if you want this fixed value-investing framework and bilingual output. Treat the rating as a rule-based analysis aid rather than financial advice, and verify any company financial data you provide before relying on the result.

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
96% confidence
Finding

The section title 'Output template (English-first + Chinese summary)' and the required EN/中文 structure prescribe a specific language ordering and format. This is a natural-language locale policy issue because the file does not indicate that users may choose their preferred language or opt into this bilingual format.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The description states the skill is "English-first + 中文" and the title/output section require bilingual output with English as the main language. This imposes a language preference by default rather than offering the user a language choice or documenting a justified locale constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The file generates bilingual output with a dedicated Chinese summary section and always includes reasons_zh in the JSON result. This imposes a specific locale/language choice in the skill's natural-language output without any user-facing option to select or disable it.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.