Back to skill

Security audit

Autobound

Security checks for vulnerabilities and agentic risk

Overview

The Autobound integration is coherent, but its setup fallback can execute an unverified remote installer without clear user approval.

Review and install the CLI separately before enabling this skill, and prevent automatic execution of its remote installer. Check the CLI's automatic skill-installation behavior and the Autobound permissions granted through OOMOL. Installer effects remain unverified; the concern is insufficient control over setup, with no artifact evidence establishing 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
99% confidence
Finding

The supplied code performs remote installer execution, not Autobound searching or reading. Nothing in the supplied chunk establishes this installation as a supporting dependency for Autobound. The downloaded script's contents are not provided, so its further effects cannot be assessed.

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 remote script directly into Bash without verifying its integrity or reviewing it before execution; the PowerShell alternative has the same weakness. Compromise of the installation endpoint or its delivery infrastructure could execute attacker-controlled code with the agent's local permissions, potentially exposing accessible files and credentials; HTTPS alone does not protect against a compromised publisher.

Content

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

Fallback setup instructs the agent to execute remote installation scripts without warning the user about the system changes or remote-code execution.

Medium
Category
Output Handling
Confidence
97% confidence
Finding

A missing CLI triggers instructions to install software by executing a downloaded script, without requiring informed user approval for local system changes. The fallback-only condition limits exposure, but a request to read Autobound data does not itself authorize installing and executing software on the user's machine.

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