ClawHub
Back to skill

Security audit

analyzing-financial-statements

Security checks for vulnerabilities and agentic risk

Overview

This skill performs local financial-ratio calculation and interpretation without hidden execution, persistence, credential access, or data exfiltration, though users should treat its investment-oriented recommendations cautiously.

Install only if you want local financial-ratio analysis from data you provide. Treat the output as educational analysis, verify all inputs and assumptions, and do not rely on the recommendations as financial, investment, tax, or legal advice.

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 (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The declared description says the skill calculates financial ratios and metrics from financial statement data. However, the provided code does not compute ratios from statements like balance sheets or income statements. Instead, it assumes ratios are already provided, then benchmarks and interprets them by industry, analyzes trends, scores overall health, generates recommendations, and formats reports. This is a materially different primary purpose: analysis/interpretation of ratios rather than calculation of ratios.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The manifest description is written only in Chinese, which indicates a language-specific skill presentation without offering the user a language choice or documenting a justified locale restriction. Under the policy, language constraints should be opt-in or clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This code generates concrete investment- and finance-oriented recommendations such as buying opportunities, valuation judgments, and capital structure actions without any visible disclaimer that the output is informational only and not financial advice. In a financial analysis skill, users may reasonably rely on these statements for real-world decisions, increasing legal, compliance, and user-harm risk if the analysis is incomplete, generalized, or wrong.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.