Back to skill

Security audit

Bank Credit Due Diligence

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only banking credit due-diligence framework that is scoped as advisory guidance and does not request tools, persistence, credentials, or system access.

Before installing, treat this as an internal analytical checklist, not an approval engine. Do not paste real customer PII or full confidential records unless your institution permits it and has proper data protections, and have qualified credit staff verify facts, calculations, regulatory requirements, and any generated rating or facility recommendation.

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
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The statement "以中文为主、关键术语保留英文" sets a default language/locale expectation for the skill. While the China-mainland regulatory scope is documented, the file does not explicitly offer users a language choice or make Chinese output an opt-in behavior, which can conflict with language/locale choice policy.

Content

No source excerpt is available for this finding.