Back to skill

Security audit

wangdongjie-cfo-skill

Security checks for vulnerabilities and agentic risk

Overview

This skill provides financial-analysis guidance, with clearly disclosed installation steps and no evidence of hidden access or automatic financial actions.

Prefer the reviewed package; inspect any version downloaded separately from GitHub before installing it. Treat the author's credentials and performance figures as unverified claims, and confirm consequential financial recommendations with a qualified adviser.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied commands perform repository retrieval and local skill installation, not financial analysis or capital-structure design. Although installation could support a separate financial skill, no such functionality is present in this chunk. The contents or behavior of the downloaded SKILL.md cannot be established from the supplied code.

Content

No source excerpt is available for this finding.