Back to skill

Security audit

Komari

Security checks for vulnerabilities and agentic risk

Overview

Komari operations have clear approval rules, but setup runs an unverified remote installer and omits broader changes the CLI can make to agent skills.

Review and install the CLI yourself before use. Its documented startup skill synchronization can be disabled with OO_SKILLS_SYNC_DISABLED=1; see the [CLI command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md). Use limited Komari permissions, check exact targets before approving changes or remote commands, and protect secret-bearing results. The remote installers and connector implementation were unavailable for inspection; no malicious behavior was established.

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 (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied code performs remote script installation rather than Komari data management. Although installing a dependency could be a supporting implementation detail, nothing in the supplied content establishes this installer as a Komari dependency. The remote script's contents and any further effects cannot be determined from this code chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The setup instructions pipe a mutable remote script directly into Bash without version pinning, integrity verification, or an opportunity to review it; the PowerShell alternative has the same weakness. Compromise of the distribution endpoint could execute arbitrary code with the agent process's privileges and expose accessible files or credentials. The missing-CLI prerequisite limits when this occurs, and HTTPS protects transport, but neither verifies that the delivered installer is trustworthy.

Content

Scanner excerpt · SKILL.md (reported line 125)May include surrounding context.

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 146)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