ClawHub
Back to skill

Security audit

Jensen

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Jensen finance reference helper that only prints static reference text and does not access data, network services, credentials, or persistent system settings.

Before installing, treat this as a lightweight reference script rather than authoritative financial or legal guidance; verify any compliance, regulation, or investment-related content against current primary sources.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The 'When to Use' section describes activation in very general terms such as 'need quick reference,' 'troubleshooting jensen issues,' and 'need a checklist or guide,' without defining clear boundaries or exclusions. This can cause unintended invocation because the trigger scope is broad and there are no negative examples or constraints explaining when the skill should not be used.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.