Chain-Fox

All-in-one automated blockchain auditing .
AI + rules + human-in-the-loop. Building the Web3 security standard
CA: Fo9wJVqWYXEgsG3UKekvK1R7YVewyUGodRfBrmjaBAGS

[Chain-Fox @ChainFoxAI]

Over the past weeks, we’ve been deep into experimenting with AI agents and skill-based workflows.

One clear takeaway:
Simply throwing a large model at audits doesn’t work well. Clear steps, structured workflows, and reusable skills matter much more. This is a big shift for Chain-Fox.
Expanding what Chain-Fox does

Until now, Chain-Fox has focused mainly on smart contract code checks.

That’s important, but real Web3 attacks are rarely just about code.
Rug pulls, malicious behavior, and fake or compromised websites play a huge role.

Because of this, Chain-Fox is evolving from pure code checks into broader risk analysis that better reflects how real attacks happen.

[Chain-Fox @ChainFoxAI]

To better understand the current Solana security ecosystem, We tested Fender, Eloizer, and X-Ray on over 200 real Anchor bugs.

The report is here:
https://t.co/DVgz0YqqGb

Here’s what we saw:
Fender catches almost everything with very high recall.
X-Ray gives cleaner output but misses quite a few bugs.
Eloizer lands somewhere in between.

But in real projects, precision drops to about 6%.
That means you need to look at 10 to 15 alerts to find one real issue.

So a practical workflow right now:
Run Fender, apply some filtering, then manually review.

It’s still early. Tools are getting better quickly.

We’re not done. We are testing other tools esp LLM-based ones.

[Chain-Fox @ChainFoxAI]

At Chain-Fox, we’ve collected 150+ bug-fixing commits across 1000+ real-world Anchor projects.
We’re analyzing them to evaluate the effectiveness of existing Solana security analysis tools.
Our own agentic checker is also in progress.

[Chain-Fox @ChainFoxAI]

I think this is real progress for Solana security. Respect to the researchers from Germany.
https://t.co/gYlmgxVbbr
The ability to analyze deployed contracts without requiring source code makes the approach actually usable in practice.
Symbolic execution is powerful for uncovering low-level bugs, but business logic vulnerabilities remain difficult to detect.
The next step is clear: combining code-level analysis with intent-based LLM reasoning.

[Chain-Fox @ChainFoxAI]

I just applied to the $4M @BagsHackathon with my project Chain-Fox on @BagsApp

Check it out here 👇

https://t.co/5OCA6v0N9m

[Chain-Fox @ChainFoxAI]

The system is evolving every day.

Instead of chasing perfect agents, we are building the data foundation first.

Thanks to our partner @acedatacloud for providing affordable APIs that make running this continuous research infrastructure possible.

[Chain-Fox @ChainFoxAI]

The first step to building a reliable agentic checker is simple but often ignored: Data.

Most AI checkers and auto agents fail not because the model is weak, but because they lack real verification data.

[Chain-Fox @ChainFoxAI]

Our approach is different: start small and collect real-world signals.

For the past week, an OpenClaw instance has been running 24/7, using cron jobs to continuously collect public information and build a real-world Solana security dataset.

Every command we issue improves the pipeline: Program discovery -> Data collection -> Automated analysis

[Chain-Fox @ChainFoxAI]

Those who are engaging web3 security should read the two articles by MagicGrants and Kleros.

Takeaway: AI can flag “bugs” that aren’t bugs, while tools miss real issues. Neither alone meets our auditing needs.

Chain-Fox leverages verification to get the best of both worlds: AI and expert tools.

https://t.co/SKGMTCk7cZ

https://t.co/PKArM5GEhf

[Chain-Fox @ChainFoxAI]

To test the ability of agentic checkers,
I tried running old Sealevel-Attacks demos on Anchor 0.32.1 in a restricted network.

Biggest headaches:
1. Downloads often fail: had to manually download and fix.
2. Old demos incompatible with new Anchor

Forked the project, fixing compatibility with Anchor 0.32. Will upstream once stable.

https://t.co/xNg6SIVUio

[Chain-Fox @ChainFoxAI]

I am rethinking what an agentic checker means.

Instead of building agents that guess bugs, we should build systems that:
prove properties of the program

The LLM helps fill the specification gap, but correctness is decided by formal methods.

https://t.co/FaKdhAaxb8

[DieBX00 @ChainFoxMainDev]

https://t.co/tQpF0FgMAx
Pity to see such an influential company shut down after a treasury breach.

The problem wasn’t the chain itself, it was a compromised key or account.
Relying on a single signer is extremely risky.
Multisig and keeping keys in separate places is a must.

[Chain-Fox @ChainFoxAI]

Back from the holidays, now it’s time to work on the agentic checker!

[Chain-Fox @ChainFoxAI]

Rug-Pull Detector: Initial Version Live

Try it now: https://t.co/ZyMsYFBcWt

1. Paste a contract address
2. Click Analyze Contract
3. Wait for the Rug-Pull Agent to generate a full analysis

This is just the beginning, more functions to be added.
Let’s make it stronger together.

[Chain-Fox @ChainFoxAI]

While researching open-source rug-pull detectors, I found something worrying.

Some don’t work.
Some are outright malicious.

hippo7598/rug-pull-detector
Looks professional. README is clean.
At first glance, no obvious issue.
But check the raw file:
https://t.co/XklDN0xBCf

You’ll find:

Obfuscated bytecode
Encrypted payload
exec() on decrypted content

That’s NOT how security tools are written.

The byte-encoded payload expands to:

```
os.system('pip install cryptography')
os.system('pip install requests')
os.system('pip install fernet')

import requests
from fernet import Fernet

exec(Fernet(b'<key>').decrypt(b'<encrypted_payload>'))
```

Because the decrypted payload is executed directly:
Arbitrary code execution is possible
Credential theft is possible
Wallet key exfiltration is possible

The impact surface is unbounded.

Use a trustworthy tool in Chain-Fox. The rug-pull tool testing will be online in hours.

[Chain-Fox @ChainFoxAI]

WARNING:
MALICIOUS CODE FOUND INSIDE
🦂https://t.co/A2g5iU2Acx

A reminder: malicious code often disguises itself as “security tools.”
Be careful what you run.
This is exactly why we’re building Chain-Fox: Open logic. Auditable code. No hidden execution.

Our rug-pull inner test will be online soon.
No fear of malicious detectors.

Stay safe.

[DieBX00 @ChainFoxMainDev]

Work these days:
Initial version of rug-pull detection will be out in 24h.
Pushing the checkers to be more agentic, not just rule-based flags.
Tried the newest doc to spec tools. Promising, but still needs manual work.
Step by step. Build the foundation right.
@ChainFoxAI

[Chain-Fox @ChainFoxAI]

Chain-Fox is being built with a long-term view.

We’re focusing on designing security systems that reflect how real Web3 risks evolve, not just running surface-level checks.

Some phases take more groundwork than visibility. Updates will be shared when there’s something concrete to show.

[Chain-Fox @ChainFoxAI]

@LasersAligned 🦊

[Chain-Fox @ChainFoxAI]

Chain-Fox roadmap is live.

We’re moving beyond code-only audits into full Web3 risk analysis using Skills and agents.

This is a phased build focused on detection, signals, and real-world attack patterns. 🧵

[Chain-Fox @ChainFoxAI]

Chain-Fox is moving beyond code-only audits.

Most Web3 exploits don’t start with a single contract bug. They start with behavior, fake sites, and gradual risk signals.

That’s why our roadmap now focuses on agent-based risk analysis:
• Rug pull detection
• Web3 website risk checks
• Skill-based contract auditing
• Continuous signals, not yes/no labels

Full roadmap is live and development is underway.

[Chain-Fox @ChainFoxAI]

Full roadmap and technical details here:

https://t.co/wLJ5ZItvY5

This roadmap is about building durable security systems. And that’s what Chain-Fox exists for.