Back to skill

Security audit

Outlook

Security checks for vulnerabilities and agentic risk

Overview

The Outlook actions have clear approval controls, but setup executes downloaded code without separate consent and may introduce broader changes to agent skills.

Review the setup before enabling this skill. Install a reviewed CLI release through a method that verifies integrity, and decide whether you want its automatic agent-skill synchronization; the [command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md) documents how to disable it. Review OOMOL's Outlook permissions and retain the required confirmations for sending, changing, and deleting data. The remote installer and hosted implementation 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
  • 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
97% confidence
Finding

The supplied chunk performs remote software installation rather than Outlook operations. Installing a CLI could be a supporting implementation detail, but the supplied content establishes no connection between this installer and the declared Outlook functionality. The downloaded script's contents and any additional behavior are not visible.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a remotely downloaded script directly into bash executes its contents with the agent's local privileges without integrity verification or review. A compromised distribution endpoint or installer could compromise accessible files and credentials; HTTPS and the legitimate dependency-setup context reduce some risks but do not establish installer integrity. The PowerShell alternative has the same underlying issue.

Content

Scanner excerpt · SKILL.md (reported line 69)May include surrounding context.

The setup workflow executes downloaded installation scripts without warning about local code execution or system changes.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

The fallback directs the agent to install software without explicitly obtaining approval for local code execution or explaining possible system changes. Restricting installation to a missing CLI reduces exposure, but authorization to manage Outlook data does not necessarily authorize installing software on the host.

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 90)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