ClawHub
Back to skill

Security audit

Portfolio Risk Sensemaker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a prompt-only crypto portfolio risk explainer with no evidence of hidden file, wallet, network, or persistence behavior.

Install only if you are comfortable typing approximate crypto holdings into the agent. Treat the output as educational risk framing, not financial, tax, or investment advice.

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
  • 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)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The declared description says the skill analyzes crypto holdings and explains risk patterns, with no permissions and prompt-only behavior. The supplied code chunk does not implement any such analysis. Instead, it is a unit test focused on security behavior: preventing local file reads when given a path-like skill_name such as '../../private-data'. Its primary purpose is validating that the handler avoids local file access and returns a safe response. That is materially different from the declared end-user functionality, so this is a clear mismatch.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.