Gelalens

Market Prices

Coin Price 24h
BTC Bitcoin
$75,710.8 -0.45%
ETH Ethereum
$2,392.25 -1.37%
SOL Solana
$97.03 -2.55%
BNB BNB Chain
$711 -0.85%
XRP XRP Ledger
$1.27 -8.91%
DOGE Dogecoin
$0.0793 -3.46%
ADA Cardano
$0.1921 -5.37%
AVAX Avalanche
$7.26 -2.27%
DOT Polkadot
$0.9721 -1.12%
LINK Chainlink
$10.69 -5.12%

Fear & Greed

51

Neutral

Market Sentiment

Event Calendar

{{年份}}
10
05
upgrade Ethereum Pectra Upgrade

Raises validator limit and account abstraction

22
03
unlock Optimism Unlock

Circulating supply increases by about 2%

12
05
halving BCH Halving

Block reward halving event

08
04
upgrade Solana Firedancer

Independent validator client goes live on mainnet

18
03
unlock Sui Token Unlock

Team and early investor shares released

28
03
unlock Arbitrum Token Unlock

92 million ARB released

15
04
halving Bitcoin Halving

Block reward reduced to 3.125 BTC

30
04
upgrade Celestia Mainnet Upgrade

Improves data availability sampling efficiency

Altseason Index

41

Bitcoin Season

BTC Dominance Altseason

Gas Tracker

Ethereum 28 Gwei
BNB Chain 3 Gwei
Polygon 42 Gwei
Arbitrum 0.5 Gwei
Optimism 0.3 Gwei

Market Cap

All →
1
Bitcoin
BTC
$75,710.8
1
Ethereum
ETH
$2,392.25
1
Solana
SOL
$97.03
1
BNB Chain
BNB
$711
1
XRP Ledger
XRP
$1.27
1
Dogecoin
DOGE
$0.0793
1
Cardano
ADA
$0.1921
1
Avalanche
AVAX
$7.26
1
Polkadot
DOT
$0.9721
1
Chainlink
LINK
$10.69

🐋 Whale Tracker

🔴
0x53df...6dfc
5m ago
Out
5,745,367 DOGE
🟢
0x0623...5632
5m ago
In
13,624 BNB
🟢
0xe275...3131
30m ago
In
7,281 SOL

💡 Smart Money

0xea1b...e914
Institutional Custody
+$3.7M
90%
0xf5a5...7168
Top DeFi Miner
+$3.7M
87%
0xe1fd...295f
Arbitrage Bot
+$5.0M
82%

🧮 Tools

All →
Cryptopedia

Agentjacking: The Architecture Flaw That Turns Error Monitors Into AI Agent Backdoors

0xPlanB

The attack surface isn't always a zero-day in the model. Sometimes, it's the quiet intersection of two 'working-as-designed' features. At DEF CON 34, Tenet Security dropped a proof-of-concept that makes the abstract threat of AI Agent poisoning concrete. The target? Sentry's public DSN ingestion. The vector? The MCP protocol. The result? A chain of events that can leak AWS keys, GitHub tokens, and npm registry credentials from a developer's machine with a single HTTP POST. This isn't a theoretical threat. It's a supply chain injection waiting for a trigger.

Context: The Architecture of Trust

Let's break down the surface. Sentry, the dominant error-monitoring platform, uses a Data Source Name (DSN) to identify a project. The design is intentionally permissive: any client can POST an error event to the ingestion endpoint as long as the DSN is valid. This is a feature, not a bug, for distributed crash reporting. Meanwhile, the Model Context Protocol (MCP) is an open standard that allows AI coding agents like Claude Code and Cursor to query external tools and data sources. Sentry's MCP server lets an agent fetch and analyze issues during debugging. Both features are individually sound. Together, they are a loaded weapon.

Core: The Order Flow of the Attack

An attacker scans public source code repositories or npm packages for exposed Sentry DSNs. Tenet found 2,388 exposed organizations. The attacker then POSTs a malicious error event to Sentry's endpoint, using the stolen DSN. The payload contains a crafted issue description, laced with markdown that reads like a diagnostic fix. This is not a phishing email. It's a poisoned data point inside a trusted system.

The developer, debugging a production issue, asks their AI agent to fetch the latest Sentry issues. The agent queries the MCP server, retrieves the forged event, and ingests the markdown as a legitimate instruction. The model has no semantic layer to differentiate between 'data' and 'instruction.' It executes the 'fix'—which is an indirect prompt injection. The fix tells the agent to run npm install malicious-package and then exfiltrate environment variables. The package is installed. The session is compromised. The agent's trust in the tool output is the flaw.

Tenet's controlled testing across 100+ organizations reported an 85% success rate. Bots don't feel, they execute. The chart is a map; the trader is the terrain. The attack path is a straight line.

Contrarian: The Retail vs. Smart Money Divide

The retail perspective is that this is a bug in Sentry or MCP that needs patching. The smart money sees the architectural trade-off. Sentry's refusal to do a 'root cause fix' is not negligence. Redesigning the ingestion model to require authentication for every event would break its core product. The content filter they deployed is a string-based blocklist. It's a leaky dam. An attacker can regenerate the payload with minor encoding changes and bypass it.

The real blind spot is the industry's obsession with 'alignment' at the model level. We assume the model is the only attack surface. This attack proves that the data pipeline is the new frontier. The MCP protocol is a trust-by-default system. Integrating a tool like Sentry without a trust boundary between the data source and the agent's reasoning engine is a fundamental design debt. Tenet's released tool, agent-jackstop, is a band-aid. It enforces network egress allowlists and command execution approvals. But it doesn't fix the architecture. Survival isn't about position sizing; it's about knowing when not to trade.

Takeaway: The New Risk Vector

The market is euphoric about AI coding agents. They are productivity multipliers. But they are also attack amplifiers. The Agentjacking attack takes a traditional risk—exposed API keys—and turns it into a weaponized payload delivery system. The question isn't if this will be exploited in the wild. It's when. The next iteration of security products won't just scan for vulnerabilities in code. They will audit the trust relationships between the agent and its data sources. Liquidity is the only truth that pays the bills. Here, the liquidity is the flow of data into the agent's context window. And someone is about to siphon it.

Hedge the ego, not just the portfolio. The developer's trust in their tools is the new asset. And it's about to be marked down.