ClawHub
Back to skill

Security audit

Implied Vol

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple local reference script, but its implied-volatility label overstates the generic finance boilerplate it actually provides.

Install only if you want a lightweight static reference stub. Do not treat its outputs as reliable implied-volatility education, trading guidance, compliance guidance, or financial advice without independent verification.

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
96% confidence
Finding

The code is benign and self-contained: it only routes CLI subcommands to heredoc text output. However, the description suggests a tool specifically for implied vol in finance. The actual content is largely templated, generic finance/operations material and lacks substantive implied-volatility-specific behavior or reference information. This is a material purpose mismatch: the implementation acts as a generic static reference stub, not a meaningful implied volatility reference tool.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The inline documentation and branding explicitly frame the script as an implied-vol reference, while the implementation delivers contradictory generic templates. In an agent ecosystem, deceptive or inaccurate self-description is dangerous because tools are often selected based on metadata and comments, so this can cause inappropriate invocation and overtrust in unsuitable content.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises itself as an implied volatility reference tool, but the exposed help and command set provide largely generic finance and operations boilerplate rather than implied-vol-specific guidance. This mismatch can mislead users and downstream agents into trusting the tool for domain-specific decisions, creating integrity and reliability risk in finance contexts where incorrect reference material may influence analysis or compliance actions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.