ClawHub
Back to skill

Security audit

Zenserp

Security checks for vulnerabilities and agentic risk

Overview

This Zenserp skill is mostly coherent, but its setup instructions can run an unverified remote installer on the user's machine without an explicit approval step.

Review before installing. Normal Zenserp searches through an already installed and authenticated `oo` CLI look scoped and coherent, but do not let an agent run the remote installer automatically. Prefer installing the CLI from a verified, versioned release or package manager, and inspect or verify any installer before execution.

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:58
Finding

Unverified Remote Installer Scripts Are Executed Directly

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 58–62
Vulnerability Type: Remote payload retrieval and execution
Risk Level: Critical

Vulnerable Code:

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 download mutable scripts from cli.oomol.com and immediately execute the responses with Bash or PowerShell. There is no pinned version, expected cryptographic hash, signature verification, or review step between retrieval and execution.

The remote scripts are not included in the audited project, so their contents and effective behavior cannot be verified from the package. Even if the domain is operated by the declared service provider, compromise of its hosting infrastructure, publishing pipeline, DNS resolution, or TLS endpoint could replace the installer with arbitrary commands after this Skill has been reviewed.

Installation is presented as a fallback when the oo command is unavailable rather than as part of every invocation. Nevertheless, executing an opaque remote response is not the minimum privilege or safest mechanism required to install the CLI. The Windows instruction has the same security properties as the Unix pipeline.

Attack Path

  1. The user or Agent attempts to invoke the Skill on a system where the oo CLI is unavailable.
  2. Following the documented fallback, it runs one of the installation commands.
  3. The system retrieves a mutable script from cli.oomol.com.
  4. The response body is passed directly to Bash or PowerShell without integrity or authenticity verification beyond transport security.
  5. If the remote distribution channel has been compromised, attacker-controlled commands execute with the privileges of the invoking user or Agent process.

Impact Assessment

A substituted ...[truncated 600 chars]

Remediation
View remediation

Remediation Suggestions

  • Remove both download-and-execute one-liners.
  • Prefer a trusted platform package manager or a signed, versioned release artifact from a verifiable repository.
  • Pin the installer or package to a specific version rather than retrieving a mutable generic URL.
  • Publish an expected cryptographic digest and require verification before execution.
  • Where supported, verify a detached signature against a documented, securely distributed signing key.
  • Separate download, verification, inspection, and execution into distinct steps.
  • Require explicit user approval before installing software or executing an installer.
  • Run installation with ordinary user privileges unless a documented operation strictly requires elevation.
  • Document the files, network endpoints, and system changes made by the installer.

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
97% confidence
Finding

The skill instructs users/agents to install software via 'curl ... | bash', which executes a remotely fetched script without prior integrity verification or review. If the hosting endpoint, transport path, or upstream distribution is compromised, this becomes a direct remote code execution path on the local machine.

Content

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

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger text is overly broad: 'Use this skill for ANY Zenserp request' and 'Whenever a task involves Zenserp' can cause the agent to invoke this skill based on loose keyword matches rather than clear user intent. That increases the chance of unintended tool use, which can expose external data flows, incur cost, or bypass safer/default handling for ambiguous requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.