Back to skill

Security audit

Keygen

Security checks for vulnerabilities and agentic risk

Overview

This Keygen integration needs review because its safety rules treat state-changing check-ins and heartbeats as harmless reads.

Correct the action classifications before using production licenses. Require authorization for check-ins and heartbeats, including starting heartbeat monitoring and its ongoing maintenance. Connect a suitably restricted Keygen account and understand that OOMOL handles its credentials and requests. Review and verify the CLI installation, including bundled agent-skill changes. The remote installer and hosted connector implementation were not audited.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied command performs remote installer execution, not Keygen data operations. Nothing in the chunk establishes this installer as a supporting dependency for Keygen. The installer contents are not supplied, so any further actions it performs cannot be determined.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

The supplied code only initiates an oo login flow and provides no evidence that it implements Keygen functionality. Authentication could be a supporting implementation detail if oo were established as a Keygen client, but the supplied content does not establish that relationship.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

The installation command pipes a mutable remote script directly into Bash without an independent integrity check or review step; the PowerShell alternative has the same execution pattern. Although this is a legitimate dependency setup step and runs only when the CLI is missing, compromise of the distribution infrastructure could execute attacker-controlled code with the invoking user's access.

Content

Scanner excerpt · SKILL.md (reported line 130)May include surrounding context.

The safety instructions classify all untagged actions as reads, but untagged check-in and heartbeat actions modify Keygen state.

Medium
Category
Excessive Agency
Confidence
98% confidence
Finding

The blanket statement that untagged actions are reads incorrectly covers check_in_license, ping_machine, and ping_process, which update check-in or heartbeat state. An agent following this classification could bypass the skill's write-confirmation requirement and affect license or process liveness without informed user approval.

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 151)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