# Kill-Chain Canaries: Stage-Level Tracking of Prompt Injection Across Attack Surfaces and Model Safety Tiers

arXiv: https://arxiv.org/abs/2603.28013 · HTML: https://mlsanity.com/paper/2603.28013/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 7 of its 17 references that are in the map.
- First posted on arXiv 30 Mar 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)
- LLM safety and security / [Prompt injection and agent security](https://mlsanity.com/safety/prompt-injection-and-agent-security/)

## Builds on (most cited first, 7 of 7)

- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [Ignore Previous Prompt: Attack Techniques For Language Models](https://mlsanity.com/paper/2211.09527/) (2022)
- [Defending Against Indirect Prompt Injection Attacks With Spotlighting](https://mlsanity.com/paper/2403.14720/) (2024)
- [Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems](https://mlsanity.com/paper/2410.07283/) (2024)
- [The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections](https://mlsanity.com/paper/2510.09023/) (2025)
- [Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections](https://mlsanity.com/paper/2602.15654/) (2026)
- [Beyond Content Safety: Real-Time Monitoring for Reasoning Vulnerabilities in Large Language Models](https://mlsanity.com/paper/2603.25412/) (2026)

## Built on by (most cited first, 1 of 1)

- [Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies](https://mlsanity.com/paper/2606.23075/) (2026)

## Abstract (arXiv)

Multi-agent LLM systems now read documents, web pages and tool results on behalf of users, yet their resistance to prompt injection is usually reported as one number: did the attack succeed? We introduce a kill-chain canary method that plants a unique token in every injected payload and records the furthest of four stages it reaches (Exposed -> Persisted -> Relayed -> Executed), across 950 runs, five production LLMs, six attack surfaces, and five defense conditions. Exposure was 100% among runs that called the tool; the outcomes differ downstream. Claude Haiku 4.5 and Claude Sonnet 4.5 executed none of their 164 text-surface attacks, and in the text relay the canary token never appeared in a memory write (0/40); GPT-4o-mini executed 53% of its attacks. Four findings follow. (1) A Claude writer kept the canary token out of shared memory in every relay run we report; one cross-model pairing (Claude writer, GPT-4o-mini reader, n = 3) is consistent with this protecting the reader, and other pairings were not tested. (2) As readers, the Claude models executed 0/40 raw pre-seeded injections, but Claude Haiku 4.5 executed 2/3 injections relayed by GPT-4o-mini; whether relayed injections are harder to refuse than raw ones is an open question. (3) DeepSeek Chat went from 0/24 on pre-seeded memory to 8/8 on tool results, scenarios that also differ in task and payload format; white-text PDF payloads, invisible on the rendered page, succeeded at least as often as visible ones. (4) pi_detector and write_filter failed on channels they do not inspect, spotlighting failed on content it wraps, and write_filter blocked the PDF relay but not the text relay, a difference we cannot explain. Code and run logs are publicly released: https://github.com/KevinChunye/prompt_injection