ClawHub
Back to skill

Security audit

Security Bond Analysis

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only bond analysis skill with disclosed data-minimization guidance and no artifact-backed behavior that reads files, calls tools, persists data, or executes code.

Before installing, treat the calculations and regulatory/current-market sections as analytical templates, not authoritative investment advice. Use your own licensed market data and compliance process, and avoid providing sensitive portfolio, client, counterparty, or nonpublic issuer information.

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 (1)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The execution-boundary section states the BondAnalyzer, portfolio, and related code are only explanatory and that the skill 'does not fetch data, does not run, and does not read/write files' (L025-L030). However, the file then presents concrete Python classes/functions with implemented calculations for pricing, YTM, duration, convexity, portfolio risk, and convertible analysis, which contradicts the characterization that these are merely non-running explanatory artifacts.

Content

No source excerpt is available for this finding.