ClawHub
Back to skill

Security audit

Oura

Security checks for vulnerabilities and agentic risk

Overview

Review is needed because setup can run downloaded software and introduce broader agent changes without a clear approval step.

Before use, review and approve the CLI installation separately and consider whether OOMOL should handle your Oura health data. Review the CLI's automatic skill installation across agent applications; its documented OO_SKILLS_SYNC_DISABLED setting disables startup skill synchronization. The installer contents and hosted implementation were not verified, and future downloads may change. [CLI controls](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md)

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 declared purpose is Oura data access, but the supplied code executes an external installer with no demonstrated connection to Oura. Remote installation and execution are not disclosed, and the chunk provides no evidence that this is a supporting implementation detail required for the declared functionality. The downloaded script's additional behavior cannot be determined from the supplied code.

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 pinning a release or verifying its integrity; the PowerShell alternative has the same execution pattern. If the distribution endpoint or publishing pipeline is compromised, following this fallback could execute attacker-controlled code with access to local files and credentials, although no compromise is established by the supplied content.

Content

Scanner excerpt · SKILL.md (reported line 89)May include surrounding context.

First-time setup executes remotely downloaded installation scripts without warning about the system-integrity implications.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The missing-CLI fallback instructs the agent to execute downloaded installation code without explaining that this permits arbitrary changes under the executing user's privileges or requiring installation approval. Although conditional and legitimate in purpose, it expands a request to read sensitive Oura data into a system-modifying operation; enforcement of the declared oo-only tool restriction could limit execution.

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 110)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