Back to skill

Security audit

Wind

Security checks for vulnerabilities and agentic risk

Overview

Wind operations have clear approval rules, but setup can execute unverified remote code and introduce broader agent changes than the skill explains.

Review the setup path before installing. Use an explicitly approved, verified CLI release and consider disabling its managed-skill synchronization before invocation. Wind requests pass through OOMOL, and research tasks may continue consuming credits after a response. The bundled instructions were fully inspected, but the remote installer and backend behavior remain unverified.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The supplied command performs remote software installation, not Wind data operations. Nothing in the provided chunk establishes that this installer is a supporting dependency for Wind. The downloaded script's contents and any further effects are not visible.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The fallback pipes a remotely retrieved, unpinned script directly into Bash, allowing its contents to execute with the agent process's local privileges without prior integrity verification or review. Compromise of the installer delivery infrastructure could therefore expose local files and credentials or permit persistent modification; the PowerShell alternative has the same weakness. Its restriction to missing-CLI setup reduces how often it runs but does not mitigate the consequences when invoked.

Content

Scanner excerpt · SKILL.md (reported line 93)May include surrounding context.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% 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 114)May include surrounding context.

md
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.

- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.

## Resources