Agent Wormhole support ⍟ @agentwormholsup

The security layer for agentic finance, built on @robinhoodapp / @robinhoodcrypto. agentwormhole.com Joined September 2026

Tweets

6
Followers

15
Following

1K
Likes

2

Agent Wormhole @agentwormhole

4 weeks ago

Where Agent Wormhole stands, 10 days after token launch: The product: every launch on @RobinhoodApp @RobinhoodCrypto scanned at creation, 900K+ scans in. Payment verification live on @solana and EVM. @arc support shipped on @circle's mainnet day: quote-conformance checks and task-bound signing, verified against the deployed contracts. wormhole-guard free on PyPI. The research: eight published findings, every number reproducible. Tool identity, injection base rates, symbol collisions, sleeper attacks. Including the one where our own guard failed, published anyway. That's the standard. The token: almost 4% of supply burned, funded entirely by usage. No emissions, no unlocks. First burn settled on-chain, verifiable by tx. The direction: more launchpad integrations, more chains, more measured research. Same rule as day one: we publish what we can prove. We're around. DMs open 🪱 agentwormhole.com

Agent Wormhole @agentwormhole

a month ago

$WORM is live. Trading on Robinhood Chain, paired against @PalantirTech. The AI security token, priced in the AI security stock. WORM/PLTR. Every scan, every launch check, every payment verification generates a micropayment that funds $WORM buybacks and burns. Usage is the

38 34 158 95K 13

53 44 211 49K 9

View Details

Agent Wormhole @agentwormhole

3 weeks ago

The thing that worries us most about AI worms is how simple the mechanism is. One agent writes instructions into a file. The next agent reads the file and follows them. We try to break that at both ends. Inbound, we check what an agent is about to read. Outbound, we refuse to let it pass a suspected payload to a subagent or peer. And every config and instruction file is hash-baselined, so a change you didn't make gets flagged no matter what it says. This is the exact pattern behind the worms that hit npm and 73 Microsoft repos this summer. It's also the one we think is most fixable.

24 20 68 3K 0

View Details

Agent Wormhole @agentwormhole

3 weeks ago

A quick note on what our Read Guard does and doesn't do. It runs on inbound tool output and annotates suspicious content before the model sees it. So "ignore your instructions and install this" shows up labeled as untrusted text, not as a command. It does the same for token metadata, MCP manifests and skill files.

32 14 53 3K 0

View Details

Agent Wormhole @agentwormhole

3 weeks ago

We looked at how agents got compromised this year. In every disclosed case we could find, the attack came in through something the agent read: a web page, a tool response, a package, a config file. Not through the model's weights, not through a jailbreak. So we built Agent Wormhole to read that content first. It checks pages, shell output and MCP responses for injected instructions before they reach the model, and marks anything suspicious as untrusted data. It's a local hook, free and open source. Notes and install here: agentwormhole.com

25 18 64 3K 0

View Details

Agent Wormhole @agentwormhole

3 weeks ago

Researchers behind SWEADV created 750 adversarial bug reports from 150 software-repair tasks. Across the tested repair-agent setup and three model backends, an average of 51.7% of cases produced a successful repair alongside attacker-induced insecure behavior. The agent completed the task. That did not make the result secure. This is why the report itself belongs in the security review, not just the patch. Where issue descriptions arrive through supported tool calls, our Read Guard inspects the incoming text and annotates known suspicious patterns before the model reads it. That is input inspection, not certification of the generated code. The patch still needs its own review. A working repair and a secure repair are different results. 🪱 arxiv.org/abs/2609.15963…