ClawHub
Back to skill

Security audit

Mem0

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for managing Mem0 through OOMOL, but its setup instructions include unverified remote installer commands that could execute arbitrary code.

Review the install step before using this skill. Prefer installing the oo CLI from a verified, pinned, or package-manager source, and do not let an agent run the remote installer automatically. Once the CLI is installed and connected, the Mem0 actions are disclosed, but write and delete requests should be approved carefully.

A.I.G

Vulnerability Patterns
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Findings (1)

T03 · Remote Payload Retrieval and Execution

Error
Location
SKILL.md:64
Finding

Unverified Remote Installer Download and Immediate Shell Execution

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 64–68
Vulnerability Type: Remote payload retrieval and execution
Risk Level: Critical

bash
curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux
powershell
irm https://cli.oomol.com/install.ps1 | iex           # Windows PowerShell

Technical Analysis

The first-time setup instructions retrieve mutable scripts from cli.oomol.com and execute the responses immediately using bash or PowerShell Invoke-Expression. Neither command pins an installer version, verifies a cryptographic signature or checksum, nor gives the user an opportunity to inspect the downloaded content before execution.

Although the download host is associated with the declared OOMOL service, remote code can change after the Skill has been reviewed. Compromise of the hosting infrastructure, publishing process, DNS resolution, TLS endpoint, or another part of the upstream supply chain could therefore turn these installation commands into arbitrary code-execution channels.

Installing the required CLI may be necessary for the Skill's functionality, but piping an unverified network response directly into a shell exceeds the minimum privileges and risk required to perform that installation.

Attack Path

  1. A Mem0 action fails because the oo CLI is not installed.
  2. The user or Agent follows the first-time setup instructions in SKILL.md.
  3. curl or irm retrieves the current installer from the remote server.
  4. The response is passed directly to bash or iex without integrity or authenticity verification.
  5. If the remote script or delivery path has been compromised, attacker-controlled commands execute with the privileges of the invoking account.
  6. The payload can access data available to that account, modify local files and configuration, install additional software, or attempt persistence and credential theft.

Impact Assessment

...[truncated 863 chars]

Remediation
View remediation

Remediation Suggestions

  1. Remove both pipe-to-shell installation commands from the Skill instructions.
  2. Prefer a trusted operating-system package manager or a reviewed, version-pinned release package.
  3. If direct download is unavoidable, separate download from execution so the artifact can be inspected:
    • Download to a newly created, non-privileged temporary location.
    • Pin an explicit release version rather than using a mutable generic installer URL.
    • Validate a publisher signature and a SHA-256 or stronger digest obtained through an independently authenticated channel.
    • Reject the artifact if any verification step fails.
    • Execute only the verified local artifact.
  4. Publish installer checksums and signing-key verification instructions in the installation guide.
  5. Avoid requesting administrator privileges unless a documented installation step strictly requires them.
  6. Keep installation as a user-initiated prerequisite rather than allowing an Agent to execute an installer automatically after a command failure.
  7. For PowerShell, avoid Invoke-Expression; save and verify the signed script before invoking it with an appropriately restricted execution policy.

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

External Script Fetching

High
Category
Supply Chain
Confidence
96% confidence
Finding

The skill instructs the agent to install software by piping a remotely fetched script directly into a shell (curl ... | bash). This bypasses integrity verification and makes execution dependent on the current contents of a remote endpoint; if that endpoint, transport chain, or hosting account is compromised, arbitrary code could be executed on the user's machine.

Content

Scanner excerpt · SKILL.md (reported line 64)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The description instructs use of the skill for any task involving Mem0, including a broad "Whenever a task involves Mem0" condition. In a markdown skill file, this is an ambiguous activation rule because it does not define boundaries, exclusions, or negative examples for when the skill should not activate.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.