ClawHub
Back to skill

Security audit

financial-report-analysis

Security checks for vulnerabilities and agentic risk

Overview

The skill does not show malicious behavior, but it should be reviewed because it produces investment recommendations from simplistic sample financial data while also disclaiming that it is not investment advice.

Install only if you want a Chinese-language financial-analysis helper and understand that its investment ratings should not be treated as professional financial advice. Verify all financial data from official sources and do not rely on the generated recommendations for trading or investment decisions.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The natural-language description, headings, usage examples, and output are entirely in Chinese, and there is no indication that other languages are supported or that the user can opt into a preferred locale. Under the policy for natural-language violations, a skill that effectively imposes a specific language without user choice should be flagged unless the locale restriction is clearly documented and justified.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The module description frames the skill as financial data retrieval and report generation, but the implementation includes investment decision guidance. This scope mismatch is risky because downstream users, integrators, or reviewers may enable the skill believing it only summarizes statements, while it actually influences investment decisions.

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’s user-facing description and outputs are written only in Chinese, and the CLI usage and report text also assume a Chinese-speaking user. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill goes beyond neutral financial report analysis and produces explicit investment ratings and recommendations such as '优秀' and '可考虑投资'. In a financial-analysis context, this is dangerous because users may rely on the output as regulated financial advice despite the simplistic scoring model and mock data source, creating compliance, misrepresentation, and user-harm risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The generated report headings, risk descriptions, disclaimer, and command-line interaction are all fixed in Chinese with no mechanism for user language choice. This creates a language-policy issue because the skill enforces one locale across user-visible behavior.

Content

No source excerpt is available for this finding.