Back to skill

Security audit

Financial Ratio Benchmarker

Security checks for vulnerabilities and agentic risk

Overview

This skill provides local, informational financial-ratio benchmarking guidance without network calls, transactions, persistence, or credential access.

Installers should understand this is an informational finance helper. It does not appear to move money or contact outside services, but users should not rely on its static benchmark examples or stock-related guidance as current or personalized financial 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
  • 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

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown file presents core skill descriptions and examples in both Chinese and English, which can impose a language expectation on users without explicitly stating how language selection works. The policy requires avoiding forced language or locale behavior unless the skill offers user choice or clearly documents the constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest sets language: en, which can signal an English-only locale policy, yet the skill includes a full Chinese scenario later in the document. This mismatch suggests an implicit language constraint without clear opt-in or documentation for multilingual behavior.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The top-level docstring presents the skill as merely providing descriptive frameworks and emphasizes that it performs no real execution or transactions. However, the implementation parses financial signals from user input and produces decision-oriented recommendations and next steps, which is more than a passive framework description. This is a contradiction in stated intent versus actual behavior, even though the behavior is still relatively low risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

Line L110 contains the comment '其他skill类似', which forces a non-English language element into the file without any indication that the skill is intended to be multilingual or region-specific. Under the language/locale policy rule, this is a natural-language policy concern because it imposes a locale choice implicitly rather than offering user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest sets the skill language to "en", which imposes a specific language/locale choice in natural-language metadata. There is no indication that users can opt into another language or that the English-only constraint is required for a justified region-specific purpose.

Content

No source excerpt is available for this finding.