Back to skill

Security audit

Checkout.com

Security checks for vulnerabilities and agentic risk

Overview

Customer-data changes require approval, but setup directs the agent to run downloaded installers without a separate approval or verification step.

Review and approve the CLI installation separately before allowing setup, including any automatic agent-skill changes. Use narrowly scoped Checkout.com access and retain approval for customer changes or deletion. OOMOL mediates the account connection and requests; the downloaded installers and server-side implementation were not verified.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied command installs software from an unrelated service and shows no Checkout.com functionality or connection establishing it as a supporting implementation detail. The remote script's contents are not supplied, so its further behavior cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command pipes a mutable remote script directly into Bash without verifying a pinned artifact or its authenticity beyond HTTPS transport. If the distribution infrastructure is compromised, attacker-controlled code could run with the agent's permissions and access local data or credentials; the legitimate dependency context and missing-CLI condition reduce exposure but do not eliminate this risk.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

Fallback installation executes downloaded scripts without a system-change warning or user approval step.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The fallback instructs the agent to install software after a missing-command error without first obtaining approval for local system changes. Although this is legitimate dependency setup and only conditionally triggered, a Checkout.com request does not itself authorize executing an installer with the agent's local permissions.

Content

No source excerpt is available for this finding.

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 79)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