Back to skill

Security audit

Product Fruits

Security checks for vulnerabilities and agentic risk

Overview

The Product Fruits reader fits its purpose, but its setup instructions execute unverified remote code without clearly explaining or approving broader system changes.

Review and approve CLI installation separately, including its automatic agent-skill changes, before allowing the setup fallback. Confirm that OOMOL should mediate access to your Product Fruits account. The remote installer contents and live connector implementation 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 executes an Oomol installation script and contains no Product Fruits search or read functionality. Nothing provided establishes this installer as a supporting dependency for the declared purpose. The remote script's contents and downstream effects are not visible, but downloading and executing it is directly evident.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

Piping an HTTPS download directly into bash executes mutable remote code without checking its contents or verifying an independently authenticated release artifact. Compromise of the distribution endpoint could yield arbitrary execution with the invoking user's permissions; the PowerShell installation example has the same risk. The legitimate dependency and conditional setup reduce exposure but do not remove this supply-chain risk.

Content

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

The setup workflow instructs execution of remote installation scripts without warning about their system-level effects.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The fallback instructs the agent to install software without first explaining the local changes or obtaining explicit approval for installation. Although triggered only when the CLI is missing, this expands a read-only data request into execution of an installer that can modify files and configuration with the invoking user's 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