Back to skill

Security audit

urlscan.io

Security checks for vulnerabilities and agentic risk

Overview

The scanning workflow requires approval for changes, but setup executes unverified remote software whose documented defaults affect other agent skills.

Review and verify the CLI installation before allowing setup to run. Check its automatic skill synchronization settings because they can affect other installed agents. OOMOL mediates account access and scan payloads; confirm the URL and scan visibility before submission. Remote installer behavior could not be verified, so this review does not establish its safety.

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
99% confidence
Finding

The supplied command runs an Oomol-hosted installer rather than interacting with urlscan.io. No connection between this installation and the declared functionality is established in the code chunk, so it represents an undeclared capability and an inconsistent resource. The installer contents are not supplied, so its further effects cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The setup procedure pipes a remotely fetched, unpinned script directly into Bash without verifying its contents or authenticity beyond HTTPS; the PowerShell alternative has the same issue. Compromise of the distribution endpoint could execute arbitrary code with the agent's local privileges and expose accessible files or credentials. Restricting this step to a missing CLI reduces exposure, but does not make execution safe.

Content

Scanner excerpt · SKILL.md (reported line 57)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 78)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