Back to skill

Security audit

Gratitude Tracker

Security checks for vulnerabilities and agentic risk

Overview

This is a simple gratitude journaling skill with disclosed user-run commands and no evidence of hidden code, exfiltration, persistence, or destructive behavior.

Before installing, consider pinning or verifying the ClawHub installer version instead of using `latest`, and note that the skill documentation is primarily Chinese. The skill itself appears aligned with gratitude journaling and does not show hidden privileged behavior.

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 Third-Party Package

Content
View full analysis

Vulnerability Details

File Location: README.md, lines 6–8
Vulnerability Type: Unpinned dependency execution through a mutable release tag
Risk Level: Medium

bash
npx clawhub@latest install gratitude-tracker

Technical Analysis

The documented installation command instructs npx to retrieve and execute the package identified by the mutable latest tag. The project does not pin an exact reviewed version, specify an integrity hash, provide a lockfile, or otherwise constrain the package artifact that will execute.

Because the latest tag can be reassigned whenever a new package version is published, the code executed by this command can change after this skill has been reviewed. This creates a supply-chain trust boundary between the documented project and the external package registry.

Attack Path

  1. An attacker compromises the clawhub package, its maintainer account, or the relevant package publication channel.
  2. The attacker publishes a malicious package release and assigns it to the latest tag.
  3. A user follows the installation command from README.md.
  4. npx downloads the attacker-controlled release from the configured package registry.
  5. Package lifecycle scripts or the invoked package entry point execute with the privileges of the user running the command.

Impact Assessment

Successful exploitation could permit arbitrary code execution under the installing user's account. Depending on that account's privileges and environment, the malicious package could access user-readable files, environment variables, credentials available to the process, network resources, and writable project or user directories.

The documented command does not itself request elevated privileges, so system-wide administrative access is not established by the available evidence. The impact is limited initially to the permissions and accessible resources of the invoking process, although exposed credentials or insecure local configurati ...[truncated 35 chars]

Remediation
View remediation

Remediation Suggestions

  1. Replace the mutable latest tag with an exact, reviewed package version, for example:
    bash
    npx clawhub@<reviewed-exact-version> install gratitude-tracker
    
  2. Verify the selected package artifact against a trusted integrity hash or package signature before execution.
  3. Use a lockfile where applicable and commit it to source control so dependency resolution is reproducible.
  4. Document the expected package registry and avoid fallback to untrusted or user-controlled registries.
  5. Review package lifecycle scripts and the resolved dependency tree before recommending the command.
  6. Run installation with the least-privileged user in an isolated environment when practical.
  7. Establish a controlled update process in which newer versions are reviewed before the documented version is changed.
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 description and all user-facing documentation in this file are written exclusively in Chinese, with no indication that the skill is region-specific or that users can choose another language. Under the stated 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
95% confidence
Finding

The README instructs users to run npx clawhub@latest install gratitude-tracker, which pulls and executes the latest version of the package manager rather than a pinned, reviewed version. If the upstream package is compromised or a breaking/malicious release is published, users may execute attacker-controlled code during installation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest description and body text use Chinese exclusively, which may impose a language/locale on users without opt-in. The policy allows language constraints only when the skill offers a choice or clearly documents a justified regional scope, neither of which appears here.

Content

No source excerpt is available for this finding.