Back to skill

Security audit

Walmart Marketplace

Security checks for vulnerabilities and agentic risk

Overview

The Walmart operations are appropriately controlled, but setup executes unverified remote code and leaves important installation effects unclear.

Verify and install a specific oo CLI release before enabling this skill, and review its automatic installation of other agent skills. Connect only the intended Walmart account and approve exact inventory replacements. The live installers' contents remain unverified; the empty static-scan results do not resolve that uncertainty.

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
93% confidence
Finding

The supplied chunk functions as a remote installer, not a Walmart Marketplace integration. It contains no marketplace requests or data operations and does not establish that the installer is a supporting dependency. The remote script's further behavior cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping the HTTPS response directly into bash executes mutable remote content without a pinned version, signature check, or review. HTTPS protects transport but does not protect against compromise of the installer publisher or hosting infrastructure; this is the same underlying installation risk identified by SQP-2, not evidence of malicious intent.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

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

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The fallback instructs the agent to execute downloaded shell or PowerShell scripts without explicit installation approval, inspection, or independent integrity verification. A compromised distribution endpoint or altered installer could execute arbitrary code with the invoking user's privileges; conditional execution reduces exposure but does not make installation safe.

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 81)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