Back to skill

Security audit

You.com

Security checks for vulnerabilities and agentic risk

Overview

The You.com workflow is coherent, but its required CLI can add persistent agent skills beyond the setup described here.

Review the broader CLI setup before installing. Use a verified release and, to prevent startup skill synchronization, set OO_SKILLS_SYNC_DISABLED=1 for every oo invocation, as documented in the [CLI reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables). OOMOL handles your connected You.com requests, which may consume credits. The installer contents and exact downloaded CLI version were not verified.

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
99% confidence
Finding

The supplied command executes an Oomol installation script and contains no visible You.com functionality. Nothing in the supplied content establishes this installer as a supporting dependency for You.com access. The script's contents and downstream effects are not provided, so those cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The setup command pipes a remotely fetched, mutable script directly into Bash without verifying a pinned version, signature, or expected digest; the PowerShell alternative has the same execution pattern. If the distribution endpoint or release pipeline is compromised, attacker-controlled code could execute with the agent's local privileges and access available files or credentials. Restricting installation to a missing-CLI error reduces exposure but does not ensure installer integrity or obtain explicit approval for local software installation.

Content

Scanner excerpt · SKILL.md (reported line 59)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 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