ClawHub
Back to skill

Security audit

blender-code-film

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rated this skill benign because its findings are limited to a disclosed setup command that may install an unpinned package; overall confidence is medium and coverage is incomplete.

Consider reviewing the package and skill contents before installing, and use a reviewed, pinned package version where possible. The scanners completed most checks, but the overall analysis is partial because two local references could not be resolved; benign does not mean risk-free.

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
87% confidence
Finding

The documented npx skills add command can download and execute an unpinned version of the skills npm package with the invoking user's permissions, exposing users to compromised future releases. This is an installation-time supply-chain risk, not an MCP server configuration as the detector suggests; its placement in a user-invoked setup example reduces immediate exposure, and there is no evidence of malicious intent.

Content

No source excerpt is available for this finding.