Back to skill

Security audit

lexoffice

Security checks for vulnerabilities and agentic risk

Overview

The accounting workflow is clearly scoped, but its setup instructions can run unchecked downloaded code without separate approval.

Review and approve CLI installation separately, including its automatic skill synchronization, before enabling this skill. Prefer a pinned, independently verified installation and retain confirmation for accounting changes. OOMOL will mediate access to your connected business data. The downloaded installer remains unverified; the supplied evidence does not establish 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 (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The supplied code installs software from an external service rather than performing lexoffice operations. Nothing in the chunk establishes this installer as a supporting dependency for the declared purpose. The downloaded script's contents and subsequent behavior are not available for assessment.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command pipes a mutable network response directly into bash without version pinning or independent integrity verification; the PowerShell alternative has the same weakness. A compromised installer endpoint or distribution pipeline could execute attacker-controlled code with the agent's privileges, potentially exposing local files and credentials. The legitimate dependency and conditional fallback reduce exposure but do not remove this supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 64)May include surrounding context.

Fallback setup executes remote installation scripts without warning about local system changes.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The missing-command fallback directs the agent to install software without first explaining local system changes or requesting installation approval. The confirmation requirements cover lexoffice writes, not local installation, so an ordinary lexoffice request could lead to unapproved execution of an installer with the agent's local privileges.

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 85)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