Back to skill

Security audit

Breathing Exercise

Security checks for vulnerabilities and agentic risk

Overview

This is a simple breathing-exercise skill with no bundled executable code, though its install command and metadata have minor disclosure and supply-chain notes.

Before installing, consider using a pinned and trusted ClawHub CLI version instead of latest, and note that the skill documentation is primarily Chinese. The unexplained curl requirement should be clarified by the publisher, but the inspected artifacts do not show exfiltration, destructive behavior, persistence, or hidden privileged actions.

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:6
Finding

Execution of an Unpinned npm CLI Dependency

Content
View full analysis

Vulnerability Details

File Location: README.md:6-8
Vulnerability Type: T08: Insecure Dependencies
Risk Level: Medium

bash
npx clawhub@latest install breathing-exercise

Technical Analysis

The documented installation command instructs users to execute clawhub through npx using the mutable latest distribution tag. If the package is not already installed locally, npx can retrieve it from the configured npm registry and execute its code immediately.

Because neither a specific reviewed version nor an integrity value is supplied, the code executed by this command can change after the skill has been audited. The project artifact contains only documentation and metadata, so the remotely retrieved CLI implementation is outside the reviewed scope. A compromised package publisher account, malicious package release, registry compromise, or unexpected update could therefore introduce executable behavior that was not present during this audit.

Attack Path

  1. An attacker compromises the clawhub package, its publisher account, or the package-distribution channel.
  2. The attacker publishes a malicious release and assigns or causes it to receive the latest tag.
  3. A user follows the installation instructions and runs npx clawhub@latest install breathing-exercise.
  4. npx downloads the mutable package release from the configured registry.
  5. Package lifecycle behavior or CLI entry-point code executes with the privileges of the user running the command.
  6. The malicious dependency can perform actions permitted to that user, such as reading accessible files, modifying user-level configuration, making network requests, or installing additional components.

Impact Assessment

Successful exploitation would provide code execution with the privileges and environmental access of the user invoking npx. For an ordinary account, the scope generally includes that user's files, credentials exposed t ...[truncated 492 chars]

Remediation
View remediation

Remediation Suggestions

  • Replace the mutable latest tag with an explicitly reviewed package version, for example npx clawhub@<reviewed-version>.
  • Verify the selected release against a trusted checksum, package signature, provenance attestation, or npm integrity metadata before execution.
  • Document the expected registry and package publisher so users can detect registry substitution or similarly named packages.
  • Prefer installing dependencies through a committed lockfile with integrity hashes rather than downloading and executing a mutable release directly.
  • Review the selected CLI package, including its executable entry points and lifecycle scripts, before recommending it.
  • In CI or other sensitive environments, execute installation with minimal privileges, restricted credentials, and limited filesystem and network access.
  • Update the audit whenever the pinned dependency version changes.
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill README presents all substantive user-facing content in Chinese, while the title is in English, and there is no indication that the skill is intended only for a Chinese-speaking or region-specific audience. This creates a natural-language policy concern because it imposes a language choice on users without opt-in or justification.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding

The installation command uses npx clawhub@latest, which pulls and executes the latest published package version at install time rather than a reviewed, pinned version. That creates a supply-chain risk: if the package or one of its resolved dependencies is compromised upstream, users may execute unexpected code during installation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description and body text are written in Chinese, including the manifest description and usage explanations, with no indication that the skill is region-specific or that users may choose another language. This can violate a language/locale policy when a skill implicitly forces one language without opt-in or justification.

Content

No source excerpt is available for this finding.