Back to skill

Security audit

LeadMagic

Security checks for vulnerabilities and agentic risk

Overview

The LeadMagic functions fit the stated purpose, but setup executes unverified downloads and leaves broader changes to agent skills insufficiently disclosed.

Review setup before enabling this skill. Install a reviewed CLI version yourself and control whether it installs or synchronizes other agent skills. Send only identifiers you intend to share with OOMOL and LeadMagic. The remote installers and hosted connector implementation were not verified; the Review verdict concerns setup authority and disclosure, not demonstrated malicious intent.

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 (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied code contains no LeadMagic operations or demonstrated connection between the Oomol installer and the declared purpose. Downloading and executing an unrelated installer is a materially different capability, not an established supporting implementation detail. The downloaded script's contents and subsequent effects are not available for inspection.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

The curl-to-bash command executes mutable remote content immediately, without artifact integrity verification or review. Although the URL belongs to the documented CLI provider and installation is only a fallback, compromise of that distribution path could expose local files and credentials or modify the system; this is the same underlying issue as the fallback-installation finding.

Content

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

The workflow sends input data to external services without warning about personal-data disclosure.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The workflow instructs the agent to execute connector actions with JSON inputs, which can include email addresses, profile URLs, and personal identifiers. Although the connector providers are named, there is no privacy warning about transmitting these inputs through OOMOL to LeadMagic, and the safety section characterizes all untagged reads as safe to run directly.

Content

No source excerpt is available for this finding.

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

Medium
Category
Output Handling
Confidence
97% confidence
Finding

The fallback instructs the agent to execute downloaded shell or PowerShell scripts without inspecting them or verifying a pinned artifact. A compromised installer endpoint or release could therefore execute arbitrary code with the agent's privileges; the missing-CLI condition limits exposure but does not remove 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 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