ClawHub
Back to skill

Security audit

ad-creative-testing

Security checks for vulnerabilities and agentic risk

Overview

The skill is rated benign because the scanners found no clear harmful behavior, though they flagged an unpinned installation command and left some reference checks incomplete.

The verdict is benign with medium confidence, not a guarantee of safety. Before installing, consider that the optional `npx skills` command may fetch an unpinned package version, and that two local references could not be resolved, leaving some evidence incomplete.

A.I.G

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

SkillSpector

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)

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

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

The documented npx skills add command can download and execute an unpinned version of the skills npm package, exposing users to malicious future releases or package compromise with the invoking user's permissions. This is an installation CLI rather than an MCP server, so the finding's categorization is inaccurate, but the underlying dependency-pinning concern is valid. Its placement in optional installation documentation, rather than an automatic execution step, reduces exposure, and there is no evidence of malicious intent.

Content

No source excerpt is available for this finding.