Back to skill

Security audit

JumpServer

Security checks for vulnerabilities and agentic risk

Overview

The JumpServer reads fit the stated purpose, but setup can execute a remote installer without separate approval or integrity verification.

Review and explicitly approve CLI setup before allowing the agent to install it. Check the CLI's documented skill synchronization and disable unwanted changes to other agent hosts. Use narrowly scoped, read-only JumpServer credentials and consider OOMOL's handling of requested records. The remote installer and connector implementation were not inspected.

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 performs remote script execution rather than searching or reading JumpServer data. Nothing in the provided code establishes that this installer is a supporting dependency for JumpServer access. The downloaded script's contents are not supplied, so its further behavior cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a remotely fetched script directly into Bash executes its contents without version pinning or independent integrity verification; the PowerShell alternative has the same issue. A compromised distribution endpoint or malicious installer update could execute arbitrary code with the agent process's privileges, potentially exposing local files and credentials. HTTPS and the missing-CLI prerequisite reduce some exposure but do not establish the installer's integrity.

Content

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

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

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The fallback directs the agent to install software when a read-oriented request encounters a missing CLI, without first obtaining approval for local system changes. Although conditional and operationally relevant, this expands the user's requested data access into execution of an installer with the current user's 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 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