Back to skill

Security audit

Deprecated Skill

Security checks for vulnerabilities and agentic risk

Overview

This deprecated skill is only a migration notice, with no executable code, but users should prefer the ClawHub install path over the unpinned npx alternative.

Install the renamed skill through ClawHub where possible. Avoid the optional npx command unless you trust the current skills npm package and the referenced GitHub repository, because that command is unpinned and global.

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:24
Finding
Unpinned Third-Party Dependency Execution During Migration## Vulnerability Details **File Location**: `SKILL.md`, lines 24–26 **Vulnerability Type**: Unpinned external package and repository installation **Risk Level**: Medium ```bash npx skills add deusyu/translate-book -a claude-code -g ``` ### Technical Analysis The documented migration command invokes the unversioned `skills` npm package through `npx` and installs Skill content from the external `deusyu/translate-book` GitHub repository. Neither the npm package version nor a Git commit is pinned, and the instructions provide no checksum or signature verification. Consequently, the resources retrieved when a user runs this command may differ from those that existed when this Skill was audited. This creates a supply-chain trust boundary in which compromise, replacement, or malicious updates of the npm package or referenced repository could cause attacker-controlled installer behavior or Skill content to be executed or installed. The `-g` option requests global installation, increasing the installed content's persistence and potential exposure across projects. ### Attack Path 1. An attacker compromises or gains publishing control over the unpinned `skills` npm package, the referenced GitHub repository, or another relevant distribution component. 2. The attacker publishes a malicious package version, installer implementation, or replacement Skill content. 3. A user follows the migration instructions and runs the documented `npx` command. 4. `npx` resolves the current unpinned package, which may differ from the reviewed version. 5. The installer retrieves and globally installs attacker-controlled repository content. 6. Any malicious behavior available to the retrieved installer or subsequently loaded Skill runs with the invoking user's permissions. ### Impact Assessment Successful exploitation could execute installer behavior under the invoking user's account or install malicious Skill instructions that affect later agent sessions. The exact privileges are lim ...[truncated 298 chars]
Remediation
## Remediation Suggestions - Pin the npm package to a reviewed, immutable version rather than invoking an unversioned package through `npx`. - Pin the source repository to a specific reviewed commit instead of a mutable branch or repository head. - Publish and verify cryptographic checksums or signatures for the installer and Skill package. - Use a verified first-party installation channel with provenance attestations where available. - Remove `-g` unless global installation is operationally necessary; prefer project-scoped installation to reduce exposure. - Document the expected package version, source commit, publisher identity, and integrity-verification procedure. - Re-audit the exact pinned installer and replacement Skill before recommending migration.
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Rp1

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding
The documentation instructs users to run `npx skills add ...` without pinning a specific package version. This can cause users to execute whatever package version is current at install time, increasing supply-chain risk if the package is later compromised or a breaking/malicious release is published. The deprecated-package context slightly reduces immediacy, but the command is still a live installation path presented to users.

Static analysis

No suspicious patterns detected.