Back to skill

Security audit

find-skills

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with high confidence: it found no AIG issues and reports one version-pinning concern in repeated `npx clawhub` examples, treated as a limited supply-chain risk rather than evidence of malicious behavior.

The verdict is benign, not risk-free. Before installing, consider whether you are comfortable with the repeated unpinned CLI commands; using a reviewed, version-pinned installation reduces the chance of running an unexpected release.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (10)

MCP server referenced without pinned version: 'npx clawhub'.

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The search command invokes an unpinned npm CLI, not an MCP server as the detector claims. If no suitable local installation exists, npx can download and execute a registry-selected release; a compromised release could run code with the agent's permissions, although nothing here indicates malicious intent.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx clawhub'.

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The browse example uses the same unpinned npm CLI execution mechanism, rather than referencing an MCP server. Browsing is benign, but npx may download and execute a compromised release before performing that operation.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx clawhub'.

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The web-search example leaves the clawhub executable's version unspecified. Although its search argument is harmless, npx can retrieve and execute an unreviewed release, creating a conditional supply-chain exposure rather than an MCP configuration issue.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx clawhub'.

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The weather-search command invokes clawhub without a version constraint. A compromised release selected by npx could execute with the agent's permissions; the benign search topic does not prevent this dependency risk.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx clawhub'.

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The document-search example can cause npx to fetch and execute an unspecified clawhub release. This is a conditional npm supply-chain weakness, not evidence of an MCP server or malicious document-processing behavior.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx clawhub'.

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The Tavily-search example executes an unpinned clawhub CLI; it does not itself install or execute a Tavily skill. The exposure is that npx may retrieve a compromised clawhub release and execute it with the agent's permissions.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx clawhub'.

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The GitHub-search example uses npx without pinning the clawhub package version. The query is benign, but a compromised package release could execute before returning search results; this is not an MCP-server reference.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx clawhub'.

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The calendar-search example leaves package selection to npx rather than specifying a reviewed release. Searching for calendar skills does not grant calendar access by itself, but execution of a compromised CLI could affect resources already accessible to the agent.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx clawhub'.

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The popularity-search command invokes the same unpinned npm CLI. Sorting by installs does not install the returned skills, but npx may still download and execute a compromised clawhub release.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx clawhub'.

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The stars-sorted search repeats the unpinned clawhub execution pattern. This creates the same conditional supply-chain exposure as the other examples, not a separate MCP vulnerability or evidence of malicious intent.

Content

No source excerpt is available for this finding.