ClawHub
Back to skill

Security audit

Budget Optimizer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward marketing budget planner, with disclosed durable memory writes that users should understand before use.

Install this if you are comfortable with the agent saving campaign budget recommendations and approved budget facts into workspace memory. Avoid providing sensitive CRM or campaign-performance data unless your host's memory and connector settings match your data-retention expectations.

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
  • 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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly instructs the agent to persist campaign inputs, outputs, and promoted facts into memory files, but it provides no requirement to obtain user consent, disclose retention, minimize stored data, or bound what gets written. In agent environments with shared or durable memory, this can cause unintended retention of potentially sensitive business information such as budgets, constraints, performance data, and scenario decisions, increasing privacy and data-governance risk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.