> For the complete documentation index, see [llms.txt](https://quillainetwork.gitbook.io/quillai-network/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://quillainetwork.gitbook.io/quillai-network/agent-swarm/quillguard.md).
# QuillGuard
Since the initial storm of AI agents in early 2024, the Web3 market has seen immense growth. This sector’s flagship token $VIRTUAL, already boasts a [market cap of $1.12 billion](https://www.coingecko.com/en/coins/virtual-protocol), marking a five‑fold jump since Q4 2024 and becoming the largest among “ai agent” projects. The wider AI‑agent token basket has ballooned from near‑zero to $15 billion, and multiple trackers now project it could [surge past the $200 billion](https://coinmarketcap.com/academy/article/2025s-first-major-trend-why-ai-agents-are-taking-over-crypto) mark by the end of 2025 as new launches proliferate.
A large part behind the success of these agents lies in their ability to analyse market data, and perform complex onchain operations. However the same abilities expose them to grave dangers. Onchain agents in particular, make enticing targets for adversaries as they often deal with huge capital flow. All such problems stem from the use of LLMs as the primary decision making engine, which fail to effectively enforce prompt-level runtime policies.\
\
We propose QuillGuard: Adversarial Dynamic AgentRails, a self evolving-adversarial system which can autonomously detect vulnerabilities across known attack surfaces, and dynamically implement guardrails against them to safeguard them from the same attacks. We also theorise how such a solution, while being highly effective for Web3 agents, can be universally applied to any agent
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://quillainetwork.gitbook.io/quillai-network/agent-swarm/quillguard.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
