ClawHub
Back to skill

Security audit

UNIHIKER K10 Box PlatformIO

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for K10 hardware development, but it installs/builds from remote dependencies that are not fully pinned or integrity-verified.

Install only if you are comfortable with a skill that can modify a target PlatformIO project, download third-party build inputs, compile firmware, and upload to connected K10 hardware. Prefer reviewing or pinning the PlatformIO platform and verifying downloaded driver file hashes before use, and run actuator tests only with the device in a safe physical setup.

A.I.G

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
scripts/install-k10-box-driver.sh:30
Finding

Remote Build Dependencies Are Not Fully Pinned or Integrity-Verified

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (1)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill instructs the agent to read local reference files, run a shell installer script, and perform PlatformIO build/upload/monitor commands, but it does not declare any explicit tool scope or permissions boundaries. That creates an over-privileged execution model where a caller may invoke file and shell-capable behavior without clear sandboxing or user-consent constraints, increasing the risk of unintended local file modification or command execution.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.