ClawHub
Back to skill

Security audit

minsky-moment

Security checks for vulnerabilities and agentic risk

Overview

This skill provides a financial-risk analysis checklist without granting transaction authority or requesting sensitive system access.

Use it as an analytical checklist and verify current source data before relying on its conclusions. Keep confidential financial details out of any saved failure-pattern notes.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 110)May include surrounding context.

md
- Lending standards loosening during the stable period (covenant-lite, rising LTV, declining coverage)
- Share of Ponzi/speculative financing growing during stability
- Risk models showing lower volatility than historical norms — trained on stability, they understate tail risk
- "Fundamentals support prices" without checking whether they generate income-based debt service capacity

## Verification

Static analysis

No suspicious patterns detected.