Back to skill

Security audit

McDonald's China

Security checks for vulnerabilities and agentic risk

Overview

The lookup functions fit the stated purpose, but setup can execute an unverified installer without clear user approval.

Review setup before enabling automatic use. Install a verified CLI release yourself and require approval for installer execution. Review its managed-skill synchronization; publisher documentation provides OO_SKILLS_SYNC_DISABLED=1 to disable it. OOMOL mediates queries and connected-account access. The full bundled artifact was inspected, but external installer and binary 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
  • 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 does not access open.mcd.cn or perform any McDonald's China data operations. It executes an external installation script, with no demonstrated connection to the declared functionality. The downloaded 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, granting the downloaded content execution privileges without prior verification. HTTPS protects transport but does not protect against a compromised publisher or hosting infrastructure; this is the concrete execution mechanism underlying the SQP-2 finding, not a separate exploit chain.

Content

Scanner excerpt · SKILL.md (reported line 61)May include surrounding context.

Fallback setup executes downloaded installer scripts without warning about system-integrity risks.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The fallback directs installation by immediately executing downloaded shell or PowerShell code without an integrity check or explicit approval for changing the host. A compromised installer source could execute arbitrary code with the invoking user's privileges; restricting this fallback to a missing CLI reduces exposure but does not eliminate the risk.

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 82)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