Back to skill

Security audit

Claw Design

Security checks for vulnerabilities and agentic risk

Overview

The skill is a minimal Chinese-language pointer to an AI design npm package, with no hidden runtime behavior in the artifact itself, but users should treat the unpinned npm install as normal third-party code risk.

Before installing, review the npm package and linked repository, consider pinning a reviewed version, and install in a low-privilege environment without sensitive credentials if you are unsure. The skill artifact itself is minimal and does not show hidden or destructive 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
SKILL.md:8
Finding

Installation of an Unverified and Unpinned Third-Party npm Package

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, line 8
Vulnerability Type: Third-party supply-chain risk
Risk Level: Medium

Complete Code Snippet:

text
npm install @self-evolving-harness/claw-design

Technical Analysis

The skill instructs users to install @self-evolving-harness/claw-design directly from the npm registry. The dependency is not pinned to an exact version, no integrity hash or lockfile is supplied, and the dependency source is not included in the audited project. Consequently, the code ultimately installed can change independently after this skill has been reviewed.

npm packages can define lifecycle scripts, such as preinstall, install, and postinstall, which may execute automatically during installation. The package implementation and lifecycle behavior could not be verified from the provided project. The referenced GitHub repository also does not, by itself, prove ownership of or correspondence with the npm scope.

Attack Path

  1. A user follows the installation instruction in SKILL.md.
  2. npm resolves the current package version from the external registry.
  3. An attacker who has compromised the package, its publisher account, or its release pipeline publishes a malicious version.
  4. npm downloads that mutable version and may execute its lifecycle scripts during installation.
  5. The malicious package executes with the operating-system permissions of the user running npm.

This path depends on compromise or malicious control of the external dependency; the audited file does not itself contain an embedded malicious payload.

Impact Assessment

A malicious dependency could execute arbitrary code under the installing user's privileges. Depending on those privileges and the host environment, this could expose accessible files, source code, environment variables, developer credentials, or authentication tokens. It could also modify project files, install additiona ...[truncated 170 chars]

Remediation
View remediation

Remediation Suggestions

  1. Pin the dependency to a reviewed exact version rather than resolving the latest release.
  2. Provide and enforce a lockfile containing registry integrity metadata.
  3. Verify that the npm publisher and scope are legitimately associated with the referenced source repository.
  4. Audit the package source, transitive dependencies, release artifacts, and npm lifecycle scripts before recommending installation.
  5. Where practical, vendor the reviewed source or distribute a reproducibly built artifact with a documented cryptographic checksum.
  6. Perform the initial dependency retrieval with lifecycle scripts disabled, such as through an appropriate --ignore-scripts workflow, and enable scripts only after review.
  7. Install and test the package in a sandbox or minimally privileged environment without production credentials or sensitive files.
  8. Use dependency monitoring and publisher-account protections to detect compromised or unexpected releases.
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 (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The visible natural-language description is entirely in Chinese and presents the skill as a Chinese-language experience without any indication that users may choose another language. Under the policy, forcing a specific language or locale without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.