ClawHub
Back to skill

Security audit

Financial Due Diligence Analyzer

Security checks for vulnerabilities and agentic risk

Overview

This is a static financial-analysis guide that does not request hidden access, execute code, persist itself, or move data elsewhere.

Install only if you are comfortable giving the agent relevant company financials. Keep the task scoped to documents you are authorized to use, ask for assumptions and citations, and have qualified finance or legal professionals review material deal decisions.

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
92% confidence
Finding

The invocation phrase 'Run financial due diligence on [company]' is very broad and provides no scope boundaries, required inputs, or exclusions. In an agent setting, this can cause over-collection of sensitive financial or company data, overly confident analysis on incomplete inputs, or unintended actions beyond passive analysis if the host agent has additional capabilities.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.