ClawHub
Back to skill

Security audit

Financial Analyst

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain financial-analysis workflow package with templates and no hidden execution or persistence behavior.

Installers should treat any requested financial files, SQL access, API keys, or web data access as sensitive and provide only the data needed for the analysis task. The package itself is coherent and does not show hidden execution, persistence, or data exfiltration behavior.

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
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • 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)

Memory Manipulation

High
Category
Memory Poisoning
Content
- Thesis ties directly to data and valuation work
- Explicit assumptions and source citations
- Clear statement of risks and downside cases
Confidence
80% confidence
Finding
Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Static analysis

No suspicious patterns detected.