ClawHub
Back to skill

Security audit

Creating Financial Models

Security checks for vulnerabilities and agentic risk

Overview

This financial modeling skill is locally scoped and purpose-aligned, with some overbroad routing and capability overstatement but no evidence of hidden or unsafe behavior.

Before installing, treat this as a basic local DCF helper rather than a complete financial advisory system. Only provide financial data you intend to use for the model, verify assumptions and formulas yourself, and note that some advertised outputs are not implemented by the included script.

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
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description is broad enough to activate on a wide range of ordinary financial-analysis requests, which can cause the agent to invoke this skill more often than intended. While the content shown is not overtly malicious, overbroad routing expands the skill’s influence and could lead to unnecessary script usage, file generation, or handling of sensitive financial data when a narrower capability would suffice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.