ClawHub
Back to skill

Security audit

Oomnitza

Security checks for vulnerabilities and agentic risk

Overview

The Oomnitza features fit the stated purpose, but setup can execute downloaded software without verification or a separate approval step.

Review before installing. Preinstall a vetted CLI release and require approval for installation or agent-skill changes. Confirm that OOMOL should receive access to the requested Oomnitza records. The bundled artifact was fully reviewed, but remote installers and hosted connector behavior remain unverified; no malicious intent is established.

A.I.G

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

SkillSpector

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 command performs a remote installation and contains no Oomnitza search or read operations. Nothing in the supplied code establishes this installer as a supporting dependency for Oomnitza access. The downloaded script's contents and any further effects are not visible.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command pipes mutable network content directly into Bash without pinning or verifying the installer. Compromise of the distribution endpoint or release process could execute arbitrary code with the agent's local privileges, exposing accessible files and credentials; HTTPS alone does not establish installer integrity.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

First-time setup instructs the agent to execute downloaded installation scripts without warning the user about the system-integrity risk.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The fallback directs the agent to execute a remote installer without explaining its system-level effects or obtaining explicit installation approval. A missing prerequisite can therefore turn a read-only Oomnitza request into local code execution; the declared tool restrictions may limit execution but do not make the installation instructions safe.

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 80)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