Back to skill

Security audit

Mandarin Chinese Daily Drill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Mandarin practice prompt with no embedded code, credential handling, persistence, or hidden behavior.

This looks safe for normal use as a Mandarin study helper. Install from a trusted registry and avoid running the `npx clawhub@latest` command with administrator privileges; pinning the installer version would reduce supply-chain risk.

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:34
Finding

Unpinned Third-Party Package Is Downloaded and Executed During Installation

Content
View full analysis

Vulnerability Details

File Location: README.md, lines 34–38
Vulnerability Type: Mutable third-party dependency execution
Risk Level: Medium

Vulnerable Code

markdown
## Installation

```bash
npx clawhub@latest install tetsuakira-vk/mandarin-daily-drill
text

### Technical Analysis

The documented installation command invokes `npx` with the mutable `clawhub@latest` version specifier. If that package version is not already available locally, `npx` retrieves it from the configured package registry and executes its CLI code. The `latest` distribution tag can be changed after this skill has been reviewed, so the code ultimately executed by users is not fixed to the audited project state.

This creates a supply-chain trust boundary: compromise of the upstream package, its publisher account, or the package registry could cause attacker-controlled code to execute when a user follows the installation instructions. No malicious package or payload is embedded in this repository; the risk arises from executing a mutable external dependency without version pinning or integrity verification.

### Attack Path

1. An attacker compromises the `clawhub` package publisher, release pipeline, or relevant registry account.
2. The attacker publishes a malicious package release and assigns it to the `latest` distribution tag.
3. A user follows the installation command in `README.md`.
4. `npx` downloads the attacker-controlled release selected by `clawhub@latest`.
5. Package lifecycle behavior or CLI initialization code executes with the privileges of the user running the command.
6. The malicious package may access or modify resources available to that user before or while processing the requested skill installation.

### Impact Assessment

Successful exploitation could provide arbitrary code execution with the privileges of the installing user. Depending on the user's permissions and environment, the affected scop
...[truncated 563 chars]
Remediation
View remediation

Remediation Suggestions

  1. Replace clawhub@latest with an explicitly pinned, reviewed version, for example:
    bash
    npx clawhub@<reviewed-version> install tetsuakira-vk/mandarin-daily-drill
    
  2. Update the pinned version only after reviewing the release provenance, changelog, and package contents.
  3. Use package-manager integrity verification, a lockfile, or a verified package hash where the installation workflow supports it.
  4. Document the expected package registry and warn users against installing from untrusted registry mirrors.
  5. Prefer a trusted, signed release mechanism and verify publisher provenance or package signatures where available.
  6. Recommend installation from a non-privileged account and avoid running the command with administrator or root permissions.
  7. In CI/CD environments, restrict network access and credentials available to the installation process to limit the impact of an upstream compromise.
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The README presents the skill as exclusively producing Mandarin practice content and aligning to HSK levels, but it does not explicitly frame the language constraint as a user choice or opt-in. Under the policy rule, forcing a specific language without opt-in is a natural-language locale/language policy concern.

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 published package version at install time rather than a pinned, reviewed release. This creates a supply-chain risk: if the package or one of its dependencies is compromised, users may execute unexpected code during installation.

Content

No source excerpt is available for this finding.