Back to skill

Security audit

Jumpseller

Security checks for vulnerabilities and agentic risk

Overview

The Jumpseller workflow requires approval for store changes, but its fallback setup directly executes downloaded code without verification or a separate approval step.

Review setup before enabling this skill. Preinstall a reviewed, verified CLI instead of allowing the fallback download-and-execute commands, and review its additional agent-skill installation behavior. Limit the connected account's access and retain confirmations for store changes. The downloaded installers and hosted 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
98% confidence
Finding

The supplied chunk performs remote script execution rather than any visible Jumpseller operation. Although CLI installation could be a supporting implementation detail, nothing supplied establishes this installer's relationship to Jumpseller. The downloaded script's contents and further 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

Piping a mutable HTTPS response directly into bash executes remote code with the agent process's privileges without verifying its integrity or reviewing its contents. HTTPS protects transport but does not prevent a compromised publisher or distribution endpoint from serving malicious code; the PowerShell example has the same underlying issue.

Content

Scanner excerpt · SKILL.md (reported line 73)May include surrounding context.

The setup workflow instructs the agent to execute remote installation scripts without warning about local system changes or remote-code execution.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The fallback directs the agent to execute remotely supplied shell or PowerShell code without an explicit approval step for local installation. Although restricted to missing-CLI errors, this expands a Jumpseller data task into local code execution, potentially exposing files and credentials if the installer or its distribution infrastructure is compromised.

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 94)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