Back to skill

Security audit

Store Leads

Security checks for vulnerabilities and agentic risk

Overview

The Store Leads workflow fits its purpose, but its fallback setup executes an unverified remote installer and leaves broader agent changes unexplained.

Review setup before installing. Prefer a separately verified CLI installation and explicitly control any installation or synchronization of other agent skills. Connect only the Store Leads access you intend OOMOL to use. The installer and downloaded binary were not audited; no malicious behavior was established.

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
  • 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
95% confidence
Finding

The supplied code performs remote software installation, not Store Leads data access. Although installing a dependency can be a supporting implementation detail, this chunk establishes no connection between the Oomol installer and the declared Store Leads functionality. The downloaded script's contents are not supplied, so its additional effects cannot be determined.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
86% confidence
Finding

The supplied chunk performs only a login operation rather than the declared Store Leads functionality. Authentication could be a supporting implementation detail if linked to Store Leads, but the supplied code establishes no such link and contains no implementation of the advertised data access.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The fallback pipes a mutable remote script directly into bash without version pinning, integrity verification, or inspection; the adjacent PowerShell alternative has the same issue. If the distribution endpoint or installer is compromised, execution can access files and credentials or modify the host with the agent's privileges; conditional execution and HTTPS reduce exposure but do not establish script integrity.

Content

Scanner excerpt · SKILL.md (reported line 60)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 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