ClawHub
Back to skill

Security audit

Black Scholes

Security checks for vulnerabilities and agentic risk

Overview

The skill does not show malware-like behavior, but it is materially misleading as a Black-Scholes finance reference because it provides generic placeholder finance content instead of Black-Scholes formulas or guidance.

Install only if you want a very generic finance-reference template. Do not rely on this skill for Black-Scholes option pricing, risk analysis, hedging, compliance, or investment decisions unless its content is corrected and independently validated.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The skill is advertised as a Black-Scholes reference tool, but the visible interface only exposes generic finance topics such as regulations, risks, instruments, and strategies, with no concrete Black-Scholes-specific calculations, formulas implementation details, or scope boundaries. This mismatch can cause an agent or user to invoke the skill in inappropriate contexts and trust outputs as quantitatively relevant to options pricing when the skill appears to function more like a generic documentation viewer.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The 'When to Use' guidance is broad and generic, encouraging invocation for vague finance-related needs without clear inclusion or exclusion criteria. In an agent setting, this can lead to over-selection of the skill, causing irrelevant, low-quality, or misleading financial guidance to be surfaced in contexts where specialized quantitative or regulatory tools are required.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The script presents itself as a Black-Scholes reference tool, but nearly all content is generic finance boilerplate rather than Black-Scholes-specific material. This is dangerous because users may rely on the tool for domain-specific financial guidance and receive misleading or incorrect information, which can cause analytical, compliance, or decision-making errors.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The formulas section strongly implies Black-Scholes calculations but instead lists unrelated generic metrics like ROI, CAGR, and Sharpe ratio. In a finance context, this mismatch increases the risk that users will apply incorrect formulas while believing they are using authoritative Black-Scholes guidance, leading to flawed pricing, hedging, or risk assessments.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.