Back to skill

Security audit

MemberVault

Security checks for vulnerabilities and agentic risk

Overview

The MemberVault actions are clearly controlled, but fallback setup runs downloaded code without separate approval or integrity verification.

Review setup before enabling this skill. Install a reviewed CLI yourself, require approval before downloaded code runs, and decide whether to disable its automatic skill synchronization. OOMOL will handle your MemberVault credentials and operation data. Keep the skill's confirmation requirements for account changes and deletions. The remote installers and hosted backend 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 (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied chunk contains only a remote installer execution command, with no MemberVault API calls or data operations. Nothing in the supplied content establishes this installer as a supporting dependency for MemberVault, so its behavior materially differs from the declared purpose. The downloaded script's additional effects cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

The only supplied behavior is an oo login command, whereas the description presents a MemberVault data-management skill. Authentication could support such an integration, but the supplied chunk provides no connection between this CLI and MemberVault. The mismatch is the unsubstantiated service and purpose alignment, not authentication itself.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a mutable remote script directly into Bash executes its contents with the agent process's privileges without prior inspection or independent integrity verification. HTTPS and the documented vendor domain reduce some risks but do not protect against a compromised distribution endpoint; the PowerShell alternative has the same exposure.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

The fallback setup executes downloaded installation scripts without warning the user about remote code execution or system changes.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The fallback instructs the agent to install software when the CLI is missing without requiring user approval or explaining that downloaded code will run and may change the local environment. The error-triggered condition limits when this occurs, but approval to perform MemberVault operations 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 79)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