Back to skill

Security audit

Vibe Coder

Security checks for vulnerabilities and agentic risk

Overview

This is a broad coding-workflow skill, but the inspected artifact is a plain Markdown guide that emphasizes planning and user confirmation rather than hidden or unsafe actions.

Before installing, understand that this skill may activate for many coding requests and can shape the agent into a slower, confirmation-heavy build process. It appears appropriate for guided greenfield coding work; continue reviewing generated code, dependencies, and commands before allowing them to run in your environment.

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
  • 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
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill description is extremely broad, covering almost any request to build software from a natural-language prompt. That can cause the skill to activate on common development-assistance requests and take over interactions beyond a narrowly scoped purpose, increasing the chance of unintended code generation or unsafe guidance in contexts that need stricter controls.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 44)May include surrounding context.

md
4. After each phase, ask: "Does this look right? Anything to change before I move on?"
5. Incorporate feedback before proceeding

Never skip a phase. Never start the next phase without confirmation.

## Phase 4 — Error Handling

Static analysis

No suspicious patterns detected.