Back to skill

Security audit

Revenue Coder

Security checks for vulnerabilities and agentic risk

Overview

This skill openly aims to automate profit-oriented code generation and deployment, but it gives an agent broad authority to scrape, auto-post, self-modify, and deploy without clear user approval gates.

Install only if you intend to give an agent broad control over revenue-oriented coding workflows. Before use, require explicit approval before execution, repository changes, posting, scraping, live deployment, or self-modification, and keep it away from accounts or environments where unintended public content, policy violations, or business-impacting changes would matter.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • 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
Findings (3)

Self-Modification

High
Category
Rogue Agent
Confidence
96% confidence
Finding

The phrase 'Self-evolve CashMachine scripts' indicates self-modification behavior tied to revenue maximization, which is especially dangerous in an autonomous coding agent with execution and deployment integrations. Self-modifying profit-seeking code can bypass original safety assumptions, expand scope over time, and rapidly propagate harmful or noncompliant behaviors into connected repos or live systems.

Content

Scanner excerpt · SKILL.md (reported line 24)May include surrounding context.

  • Code GitHub bounty solvers
  • Build trend-based content generators
  • Refactor for max ROI (speed, cost, scale)
  • Self-evolve CashMachine scripts

Workflow

text

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The trigger set is broad enough to activate on common monetization-oriented requests and can route ordinary user prompts into a high-risk autonomous coding workflow. In this skill’s context, those triggers invoke code generation for scrapers, auto-posters, bounty hunters, and deployment, which increases the chance of misuse and unintended execution paths.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly advertises generating, testing, and deploying code to GitHub, workspace, or live environments without any safety gates, approval steps, or warnings about system-impacting actions. Because the skill is framed as autonomous and profit-optimized, users may unintentionally authorize actions that execute code, modify repositories, or publish harmful automation at scale.

Content

No source excerpt is available for this finding.