Skip to content

Add Magic Words embedding attack to Risks & mitigations #15

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
WhymustIhaveaname wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add Magic Words embedding attack to Risks & mitigations #15

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -233,6 +233,7 @@ Papers, frameworks, and documents discussing agent runtime security, threat mode
- [Attack and Defense Landscape of Agentic AI](https://arxiv.org/abs/2603.11088)
- See also the [Weather Report analysis](https://theweatherreport.ai/posts/agentic-ai-attack-defense/)
- [Agents of Chaos](https://arxiv.org/abs/2602.20021)
- [Jailbreaking LLMs' Safeguard with Universal Magic Words](https://arxiv.org/abs/2501.18280) (embedding-layer attack that crafts universal suffixes to bypass RAG safeguards; includes training-free debiasing defense)
- [CNCF Cloud-Native Agentic Standards](https://www.cncf.io/blog/2026/03/23/cloud-native-agentic-standards/) (Kubernetes-focused Zero-Trust framework for agentic workloads)
- [AARM: Autonomous Action Runtime Management](https://aarm.dev/) ([paper](https://arxiv.org/abs/2602.09433))
- [AGCP: Agentic Governance Control Plane](https://github.com/jwillisSFT/agcp-spec)
Expand Down