Back to skill

Security audit

Contact Manager

Security checks for vulnerabilities and agentic risk

Overview

This is a simple contact-management skill with disclosed contact import/export behavior, but users should be careful with exported personal data and the mutable installer command.

Install only from a trusted ClawHub/npm source, prefer a pinned installer version when available, and treat exported contact files as sensitive because they may contain names, phone numbers, emails, and relationship data.

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

Mutable npm Package Version Executed During Installation

Content
View full analysis

Vulnerability Details

File Location: README.md, lines 5-7
Vulnerability Type: Unpinned third-party installation dependency
Risk Level: Medium

bash
npx clawhub@latest install contact-manager

Technical Analysis

The documented installation command instructs npx to retrieve and execute the package version referenced by the mutable latest npm distribution tag. Because neither an immutable version nor an integrity value is specified, the code executed by this command may change after the Skill has been audited.

This creates a supply-chain risk: compromise of the package publisher, npm account, release pipeline, or a future release assigned to latest could cause users to execute code that was not included in the reviewed project. The repository itself contains no executable implementation that can establish or constrain the behavior of the downloaded installer.

Attack Path

  1. An attacker compromises the clawhub npm publisher account, release pipeline, or another mechanism controlling the latest package release.
  2. The attacker publishes a modified package and assigns it to the latest distribution tag.
  3. A user follows the installation command in README.md.
  4. npx downloads and executes the attacker-controlled package version.
  5. The package runs with the operating-system privileges of the user invoking the command and may access resources available to that user.

Impact Assessment

Successful exploitation could permit arbitrary code execution with the installing user's privileges. Depending on those privileges and the host environment, the downloaded package could access user-readable files, environment variables, credentials available to the process, network resources, or project data. System-wide impact would require the installation command to be run by a privileged user or an additional privilege-escalation mechanism.

No evidence in the reviewed files establishes that th ...[truncated 135 chars]

Remediation
View remediation

Remediation Suggestions

  • Replace clawhub@latest with an explicitly reviewed, immutable package version, such as clawhub@x.y.z.
  • Publish and verify package integrity information or cryptographic signatures where supported.
  • Document the expected npm registry, package publisher, and package provenance so users can validate the source.
  • Use lockfiles or equivalent dependency controls in automated installation workflows.
  • Establish a process for reviewing each new installer version before updating the documented command.
  • Advise users not to run the installer with elevated privileges unless those privileges are strictly required.
  • Remove the unexplained curl binary requirement from _meta.json, or document and constrain its legitimate purpose, to minimize unnecessary tooling and ambiguity.
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file advertises '批量导入导出' as a skill capability, which implies handling potentially sensitive personal contact information. The description provides no user warning about data privacy, overwriting, or external file creation despite the feature affecting user data.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The export section explicitly lists CSV, VCF, and JSON output formats, indicating that user contact data can be written to disk or shared. The markdown does not disclose any privacy or data-handling implications of exporting personal information.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill description and headings are presented in Chinese, which can amount to a language policy issue when no user opt-in or locale justification is provided. There is no indication that the skill is region-specific or that other language options are available.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The manifest does not define any specific trigger scope, activation constraints, or limiting conditions, which means the skill may be callable in broader contexts than necessary. For a contact-management skill that may access sensitive personal data, overly broad activation increases the chance of unintended invocation or misuse by other workflows.

Content

No source excerpt is available for this finding.