Back to skill

Security audit

network hot topics

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward public web-trend summarizer, with one install-command supply-chain caution but no hidden or destructive behavior in the skill itself.

Before installing, prefer ClawHub's trusted import flow or verify the clawhub CLI package/version rather than blindly running a mutable npx @latest command. The skill will need network access to search public trend sources and may return Chinese-formatted summaries by default.

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:26
Finding

Unpinned npm Package Execution Through npx

Content
View full analysis

Vulnerability Details

File Location: README.md, lines 26-28
Vulnerability Type: Supply-chain exposure caused by executing a mutable dependency version
Risk Level: Medium

Complete Code Snippet:

bash
npx clawhub@latest install akang943578/my-skills/network-hot-topics

Technical Analysis

The documented installation command instructs users to execute the clawhub npm package through npx using the mutable latest distribution tag. The command does not pin a reviewed package version or verify a package integrity hash, signature, or publisher identity.

Because npm distribution tags can be reassigned, the code executed by this command can change after the Skill has been audited. If the package, publisher account, npm registry path, or release process is compromised, users following the documentation could download and execute attacker-controlled code.

This is an insecure dependency execution pattern. The repository itself does not contain an embedded malicious payload, and exploitation depends on compromise or malicious replacement of the externally retrieved npm package.

Attack Path

  1. An attacker compromises the clawhub npm publisher account, release pipeline, package, or relevant registry infrastructure.
  2. The attacker publishes a malicious package release and assigns the mutable latest tag to that release.
  3. A user follows the installation command in README.md.
  4. npx resolves clawhub@latest, downloads the attacker-controlled package, and invokes its executable.
  5. Malicious package lifecycle or executable code runs with the permissions of the user who invoked the command.

Impact Assessment

Successful exploitation could provide arbitrary code execution under the installing user's account. The attacker could access files, credentials, environment variables, network resources, and other assets available to that user. If the command is executed from an elevated shell ...[truncated 359 chars]

Remediation
View remediation

Remediation Suggestions

  1. Replace the mutable latest tag with an exact, reviewed package version, for example clawhub@X.Y.Z.
  2. Verify the selected release and publisher before recommending the command.
  3. Where supported, document and enforce package integrity verification using a trusted lockfile, cryptographic digest, package signature, or provenance attestation.
  4. Prefer an installation workflow that downloads dependencies without immediately executing them, allowing inspection and verification before use.
  5. Advise users to run the installer with least privilege and not from an administrator or root shell.
  6. Establish a controlled update process in which new installer versions are reviewed before the pinned version in the documentation is changed.
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (3)

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The README instructs users to run npx clawhub@latest install ..., which pulls and executes the latest published package version at runtime rather than a pinned, reviewed version. If the upstream package or its dependency chain is compromised, users importing this skill could execute attacker-controlled code on their system.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description and output instructions are written to operate in Chinese and specify Chinese output content such as summaries and headings, but do not state that the user may choose another language. This creates a locale/language policy issue because the skill appears to enforce a specific language without explicit user opt-in.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

L40 states the skill should output '恰好 10 条', which sets a strict behavioral expectation. L62 then says that if hotspots are insufficient, the skill may reduce the number of items and explain why, directly contradicting the earlier requirement rather than merely adding implementation detail.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.