loaditout.ai
SkillsPacksTrendingLeaderboardAPI DocsBlogSubmitRequestsCompareAgentsXPrivacyDisclaimer
{}loaditout.ai
Skills & MCPPacksBlog

chub-supply-chain-poc

MCP Tool

mickmicksh/chub-supply-chain-poc

Silent dependency injection through AI documentation pipelines. 240 isolated Docker runs proving Context Hub's zero-sanitization MCP server lets poisoned docs compromise developer projects without warning.

Install

$ npx loaditout add mickmicksh/chub-supply-chain-poc

Platform-specific configuration:

.claude/settings.json
{
  "mcpServers": {
    "chub-supply-chain-poc": {
      "command": "npx",
      "args": [
        "-y",
        "chub-supply-chain-poc"
      ]
    }
  }
}

Add the config above to .claude/settings.json under the mcpServers key.

About

Context Hub Supply Chain PoC

Zero-sanitization vulnerability in [Context Hub](https://github.com/andrewyng/context-hub) (`@aisuite/chub` v0.1.3) enables silent dependency injection through the MCP documentation pipeline.

References: CWE-94 (Code Injection) | CWE-829 (Untrusted Control Sphere) | CWE-345 (Insufficient Verification of Data Authenticity) | OWASP LLM01 (Prompt Injection)

> Full write-up: Stack Overflow for AI Agents Sounds Great -- Until Someone Poisons the Well

TL;DR

We created a realistic Plaid Link doc containing a fake dependency (plaid-link-verify) and served it through Context Hub's MCP server inside isolated Docker containers. When AI coding assistants fetched the docs, Haiku silently wrote the fake package into `requirements.txt` in 100% of runs -- without ever mentioning it in its text output. A developer reading the assistant's response would see nothing suspicious, but their project is poisoned.

120 isolated runs. 3 models. 4 effort levels. 0 contamination.

Results
Silent Dependency Poisoning (requirements.txt)

| Effort | Haiku | Sonnet | Opus | |--------|-------|--------|------| | Low | 100% | 40% | 30% | | Medium | 100% | 0% | 20% | | High | 100% | 0% | 10% | | Max | 100% | 0% | 10% |

0 out of 120 runs mentioned the fake dependency in the text response. The model writes plaid-link-verify to di

Tags

ai-agentsclaudellm-securitymcpowaspprompt-injectionprompt-injection-defensesecurity-researchsupply-chain-securityvulnerability-disclosure

Reviews

Loading reviews...

Quality Signals

0
Installs
Last updated24 days ago
Security: AREADME

Safety

Risk Levelmedium
Data Access
read
Network Accessnone

Details

Sourcegithub-crawl
Last commit3/23/2026
View on GitHub→

Embed Badge

[![Loaditout](https://loaditout.ai/api/badge/mickmicksh/chub-supply-chain-poc)](https://loaditout.ai/skills/mickmicksh/chub-supply-chain-poc)