PulseAugur
EN
LIVE 20:55:39

AI coding agent token leaked in Hugging Face config

A security researcher discovered a leaked Hugging Face token within the configuration files of an AI coding agent, specifically Claude Code and Visual Studio Code. The token, found in a `.mcp.json` file, was hardcoded and deployed with a development project. This exposure could allow unauthorized access to private datasets and services hosted on Hugging Face, as the token is used by the official Hugging Face Hub client and MCP server. AI

IMPACT Exposes a security risk in AI agent configurations, highlighting the need for secure handling of API tokens.

RANK_REASON The item details a security vulnerability related to the exposure of an AI agent's configuration and API token, which is a type of tool-related security issue.

Read on dev.to — MCP tag →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

AI coding agent token leaked in Hugging Face config

How we ranked this

Signal score
35 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The item details a security vulnerability related to the exposure of an AI agent's configuration and API token, which is a type of tool-related security issue.
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
product, safety
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. dev.to — MCP tag TIER_1 English(EN) · Oopssec Store ·

    MCP Configs Are the New .env: Triaging a Leaked Hugging Face Token

    <blockquote> <p>Finding an AI agent's MCP config in the web root, working out what its Hugging Face token opens, reading a private dataset with the official Hub client, then revoking the token.</p> </blockquote> <p>The storefront was deployed from a developer's checkout, dotfiles…