Back to skill

Security audit

MailBluster

Security checks for vulnerabilities and agentic risk

Overview

Review is needed because setup can execute an unverified remote installer without separate approval or explaining its broader changes to your agent.

Review and approve CLI installation separately. Check which additional agent skills it installs before connecting MailBluster. The [CLI documentation](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md) describes OO_SKILLS_SYNC_DISABLED for preventing startup skill synchronization. MailBluster writes and deletion already require approval. No malicious behavior was established, but the external installer remains uninspected.

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 code performs remote installer execution rather than any visible MailBluster operation. Nothing in the provided content establishes this installer as a supporting dependency for MailBluster functionality. The downloaded script's contents are not supplied, so its further behavior cannot be assessed.

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 response directly into Bash without verifying a pinned artifact or signature; the PowerShell alternative has the same trust problem. Compromise of the distribution endpoint or release pipeline could therefore execute attacker-controlled code with the user's privileges, although HTTPS and the conditional setup path reduce some exposure.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

The setup workflow executes downloaded installer scripts without warning about local system changes.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

When the CLI is missing, the setup instructions direct installation without requiring approval for executing downloaded code or explaining local system changes. Installation executes with the invoking user's privileges and may modify files or access sensitive data; limiting setup to missing-CLI errors reduces exposure but does not establish user consent.

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 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