Back to skill

Security audit

Password Manager

Security checks for vulnerabilities and agentic risk

Overview

This password-manager skill is purpose-aligned, but it handles passwords and recommends a mutable installer without enough detail about storage, network checks, auto-fill safety, or package verification.

Review this carefully before installing. The advertised function is a password manager, so only use it if you trust the publisher and can verify the installer version. Prefer a pinned install command, confirm how passwords are stored and encrypted, understand whether breach checks or cloud sync send any data off-device, and avoid displaying or auto-filling secrets in untrusted environments.

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

Unpinned Third-Party Package Execution via npx

Content
View full analysis

Vulnerability Details

File Location: README.md:6
Vulnerability Type: Unpinned executable dependency
Risk Level: Medium

bash
npx clawhub@latest install password-manager

Technical Analysis

The documented installation command instructs users to download and execute the package currently associated with the mutable latest tag. No exact version, integrity hash, lockfile, or package provenance verification is provided.

Because the effective package content can change after this skill has been reviewed, a compromised maintainer account, package registry, or future package release could cause the command to execute code that was never included in this audit. This is a supply-chain risk rather than evidence that the package currently published as clawhub@latest is malicious.

Attack Path

  1. An attacker compromises the clawhub package, its publisher account, its release pipeline, or the relevant package registry entry.
  2. The attacker publishes a malicious release and assigns it the latest distribution tag.
  3. A user follows the installation instruction in README.md.
  4. npx retrieves the attacker-controlled package version and invokes its CLI or applicable installation behavior.
  5. The malicious package executes with the permissions of the user running the command.

Impact Assessment

Successful exploitation could permit arbitrary code execution under the invoking user's account. Depending on that user's permissions and local environment, the package could access user-readable files, credentials, environment variables, developer tokens, and network resources; modify user-owned data or configuration; or install additional payloads. Administrative privileges are not inherently obtained by this command, but impact would increase if a user runs it from a privileged account or environment.

Remediation
View remediation

Remediation Suggestions

  • Replace the mutable latest tag with an exact, audited package version.
  • Document the expected registry and verified publisher identity.
  • Provide a package integrity digest or signed provenance information and require verification before execution.
  • Review the pinned package, including lifecycle scripts and transitive dependencies, before recommending it.
  • Where supported, disable unnecessary package lifecycle scripts and use a lockfile or equivalent dependency integrity mechanism.
  • Update the pinned version only through a controlled review process, followed by renewed security verification.
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The user-facing skill description and instructions are written entirely in Chinese, but the file does not state that the skill is region-specific or provide any language/locale choice. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
97% confidence
Finding

The README instructs users to run npx clawhub@latest install password-manager, which pulls and executes the latest published package version at install time. For a password-manager skill, this is especially sensitive because a compromised or malicious upstream release could execute arbitrary code on the user's machine and potentially access secrets or passwords during installation or setup.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This skill handles highly sensitive credential material but provides no warnings about secure handling, clipboard or terminal exposure, shared-device risks, or the dangers of auto-fill on untrusted sites. In a password-manager context, omission of these safety notes can lead users to expose passwords or misunderstand the trust boundaries of storage and auto-fill behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The skill metadata and body are written entirely in Chinese, with no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking audience. This can constitute a language/locale policy issue because the skill appears to impose a single language without opt-in or justification.

Content

No source excerpt is available for this finding.