Back to skill

Security audit

Screendesk

Security checks for vulnerabilities and agentic risk

Overview

The Screendesk workflow is coherent, but its automatic remote installation step and under-disclosed changes to agent skills warrant review.

Review and install the CLI yourself before allowing this skill to run. Check whether its automatic skill synchronization is acceptable; the documentation provides OO_SKILLS_SYNC_DISABLED to disable it. OOMOL mediates access to your connected Screendesk account, so grant only the permissions needed and confirm recording updates. The remote installer contents and exact release behavior remain unverified.

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
  • 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 chunk performs remote software installation rather than the declared Screendesk data operations. Although installation can be a supporting implementation detail, nothing supplied connects this Oomol installer to Screendesk. The downloaded script's contents and subsequent effects cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command streams a mutable remote script directly into Bash without verifying its integrity or reviewing it; the PowerShell alternative uses the same fetch-and-execute pattern. Compromise of the distribution endpoint or release process could execute arbitrary code with the invoking user's permissions, although the legitimate dependency and HTTPS URL provide no evidence of malicious intent.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

First-time setup executes downloaded installation scripts without warning the user about remote-code execution or system changes.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

On a missing-command error, the skill instructs the agent to install software without first obtaining approval or explaining that downloaded code will execute and may modify the local environment. Restricting installation to first-time setup reduces exposure, but authorization to access Screendesk does not necessarily authorize local software installation.

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 81)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