ClawHub
Back to skill

Security audit

Ortto

Security checks for vulnerabilities and agentic risk

Overview

The Ortto features fit their purpose, but automatic setup can execute downloaded code without separate approval or clear limits on local changes.

Review and approve CLI installation separately, preferably using a verified release. Check or disable bundled-skill synchronization before use; the [command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md) documents OO_SKILLS_SYNC_DISABLED. Confirm you accept OOMOL handling Ortto requests and credentials, and retain confirmation for contact changes. Exact remote installer effects remain unverified.

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
99% confidence
Finding

The supplied code performs remote installer execution rather than Ortto data operations. Nothing in the chunk establishes that the Oomol installer is a supporting dependency for Ortto. The remote script's contents are not supplied, so its further behavior cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a mutable remote script directly into bash executes its contents without prior inspection or integrity verification. Although the domain is relevant to the documented connector platform and HTTPS protects transport, a compromised distribution endpoint or malicious script update could execute arbitrary code with the agent's permissions.

Content

Scanner excerpt · SKILL.md (reported line 57)May include surrounding context.

Automatic CLI setup executes downloaded scripts without warning about their system-level effects.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

On a missing-CLI error, the skill directs the agent to execute a downloaded installer without requiring explicit approval for local system changes or explaining its execution privileges. The fallback-only condition reduces exposure, but an ordinary Ortto request could still trigger arbitrary installer code running with the agent's local permissions.

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 78)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