ClawHub
Back to skill

Security audit

Best Buy

Security checks for vulnerabilities and agentic risk

Overview

The Best Buy lookups are read-only, but automatic setup executes an unverified remote installer without a separate approval step.

Review and approve CLI installation separately before enabling this skill. Verify the installer or release, check which agent skills the CLI installs or updates, and disable synchronization if unwanted. Best Buy queries and account authorization go through OOMOL and may use credit. The packaged instructions were fully inspected, but the remote installers and hosted runtime were not verified.

A.I.G

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

SkillSpector

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 (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

Installing the CLI is a relevant prerequisite rather than an unrelated hidden behavior, but the fallback instructs the agent to execute mutable remote scripts without verification or explicit user approval. If the installer or its distribution infrastructure is compromised, an otherwise read-only Best Buy task could execute arbitrary code with the agent's local privileges; this overlaps with the SC2 finding.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

The supplied chunk performs only a login operation and contains no Best Buy-specific search or reading behavior. Authentication could support the declared purpose, but the provided code does not establish that relationship; its sole demonstrated function is authentication.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping an HTTPS response directly into Bash executes remote code without inspecting or authenticating the downloaded artifact. Although limited to missing-CLI setup and hosted on the expected vendor domain, a compromised installer endpoint or release pipeline could gain code execution with the agent's privileges; the PowerShell example has the same weakness.

Content

Scanner excerpt · SKILL.md (reported line 62)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 83)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