Back to skill

Security audit

Dream Tracker

Security checks for vulnerabilities and agentic risk

Overview

This is a simple dream journal skill with no embedded executable code, though users should be cautious with the unpinned installer and any exported personal dream data.

Install only if you are comfortable running the visible ClawHub npm installer, preferably with a pinned trusted version when available. Treat dream entries and exports as private personal data, and review where any analysis or sharing feature sends or stores content before using it.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
README.md:5
Finding

Execution of an Unpinned npm Package During Installation

Content
View full analysis

Vulnerability Details

File Location: README.md, lines 5–9
Vulnerability Type: Supply-chain risk caused by unpinned package execution
Risk Level: Medium

Complete Code Snippet:

markdown
## 安装

```bash
npx clawhub@latest install dream-tracker
text

### Technical Analysis

The documented installation command invokes `npx` with the mutable `latest` tag:

```bash
npx clawhub@latest install dream-tracker

Depending on the local npm configuration and cache state, npx can retrieve the current clawhub package release from the configured npm registry and execute its command. The latest tag can be changed after this skill has been reviewed, so the code eventually executed by users is not cryptographically or immutably tied to the audited project version.

The repository supplies no exact dependency version, lockfile, package integrity hash, signature verification procedure, or vendored installer implementation. Consequently, an npm account or package compromise, malicious release, registry substitution, or unexpected future package change could expose users to code that was not included in this audit.

This finding concerns the documented external installer rather than embedded malicious code in the reviewed project. No evidence establishes that the current clawhub package is malicious.

Attack Path

  1. An attacker compromises the npm package publisher, publishing credentials, registry, or another component capable of controlling the package associated with clawhub@latest.
  2. The attacker publishes a malicious package version and assigns the mutable latest distribution tag to it.
  3. A user follows the installation command in README.md.
  4. npx resolves and downloads the attacker-controlled release when it is not already available from a trusted local cache.
  5. The downloaded package executes through the clawhub command and can perform actions with the privileges of the user ...[truncated 725 chars]
Remediation
View remediation

Remediation Suggestions

  1. Replace the mutable latest tag with an exact, reviewed package version, for example:

    bash
    npx --yes clawhub@X.Y.Z install dream-tracker
    
  2. Publish and verify the expected package integrity hash or signature through a trusted channel.

  3. Document the expected npm registry and require secure registry transport to reduce registry-substitution risk.

  4. Prefer a lockfile-backed installation workflow where applicable, and review dependency changes before updating the pinned version.

  5. In CI or other sensitive environments, execute the installer with a minimally privileged account, restricted credentials, and network or filesystem isolation.

  6. Avoid instructing users to run the installation command as an administrator or root user.

  7. Consider distributing a reviewed local installer or package artifact whose contents can be verified before execution.

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill description and section headings are presented in Chinese, and there is no indication that users can choose another language or that the skill is intentionally limited to a Chinese-speaking or region-specific audience. This creates a natural-language policy concern because it imposes a specific language without opt-in.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

The installation command uses npx clawhub@latest, which pulls and executes the latest package version at install time rather than a pinned, reviewed version. This creates a supply-chain risk: if the upstream package is compromised or a breaking/malicious release is published, users may execute untrusted code simply by following the README.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The natural-language content and examples are entirely in Chinese, which can amount to a language/locale policy violation when no user opt-in or alternative language support is offered. The file does not state that the skill is intentionally region-specific or provide a language choice.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill advertises an export/share capability for highly personal dream data but provides no warning about privacy implications, consent, or where shared data may go. Because dream entries can contain sensitive mental-health, relationship, or identity information, omission of a privacy notice can lead users to disclose personal data without understanding the risk.

Content

No source excerpt is available for this finding.