Security audit

H1B Sponsor Finder

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only H1B sponsor lookup skill with a reasonable purpose; the main caution is its unpinned npx install example.

Before installing, consider using a pinned or otherwise trusted ClawHub CLI version rather than blindly running an unversioned npx command. Once installed, treat its H1B results as research leads only, since the skill itself says the data may be delayed or incomplete and is not legal or immigration advice.

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: README.md:50
Finding: Unpinned Package Execution Through npx
Content: View full analysis
Remediation: View remediation

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)

Rp1

Medium

Category: MCP Rug Pull
Confidence: 90% confidence
Finding: The README instructs users to run npx clawhub install h1b-finder without pinning a specific version of the package being executed. That means users may fetch and run whatever version is current at install time, creating a supply-chain risk if the package or a dependency is ever compromised or unexpectedly changed. In this context, the risk is somewhat elevated because the command is presented as a direct installation step for end users.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.