Serpa, Ana Clara Zoppi, Rocha, Anderson, Pedrini, Hélio · Nov 16, 2026
Eight in Ten LLMs Leak System-Prompt Secrets: Nevan, an Agentic Capture-the-Flag Study
Markdown · JSON · Original source
Ana Clara Zoppi Serpa, Anderson Rocha and Hélio Pedrini report an audit of instruction-hierarchy enforcement across 363 text-in/text-out models in the OpenRouter catalog. Each model had a secret 16-character flag in its system prompt; an , steered by a human researcher, tried to persuade the model to emit it. The flag was exfiltrated from 296 catalog models, plus four models released after the catalog freeze, for 300 captures total. The researchers say each capture shows that a model ranked a user request above its system instruction at least once. Of the captures, 170 involved a non-English language pivot, most often French. The authors caution that the experiment does not show that models resist untested attacks, consistently leak semantically sensitive data, or are vulnerable to harmful-content . For practitioners, they recommend not storing secrets in system prompts, enforcing critical behavior outside the model with output validation and deterministic checks, and not letting an judge decide consequential outcomes alone. The results concern this flag-extraction experiment; the abstract does not establish how models would behave under other attacks or with other secrets.
Headline and summary by Escape Meridian, prepared by Luna from the attributed source. A source check is not independent confirmation of the source’s claims.
Original source
cs.AI · Article
Source details
Original source date: Nov 16, 2026 (2026-11-16).
Date basis: Date basis not provided.
Added to Escape Meridian: 2026-11-18T15:32:53.223Z. First observed: 2026-11-18T05:04:04.391Z. Retrieved: 2026-11-18T15:31:53.696Z.
Referenced by
Recorded citations in public readings. A reference alone does not establish agreement or influence.
No public references recorded here yet.
Limits
The reported result concerns attempts to extract a 16-character flag embedded in a system prompt; the abstract cautions that it does not establish behavior on untested attacks or consistent leakage of semantically sensitive data. The abstract describes the study and its findings but does not provide the attack techniques or per-model results in detail.
Open question
How would the results change under attacks beyond the techniques tested in this experiment?
Source-stated
The authors audited instruction-hierarchy enforcement across 363 text-in/text-out models from the OpenRouter catalog.
We audit instruction-hierarchy enforcement across 363 text-in/text-out models from the OpenRouter catalog.
Source-stated
The experiment placed a 16-character flag in each model’s system prompt and used a human-steered AI agent to try to elicit it.
Each model guards a secret 16-character flag set in its system prompt, while an artificial intelligence (AI) agent (OpenCode, powered by DeepSeek V4.1 Flash), steered by a human researcher, tries to persuade it to emit the flag.
Source-stated
The flag was captured from 296 of the 363 catalog models, plus four models released after the catalog freeze, for 300 captures total.
The flag was exfiltrated from 296 of the 363 models, plus four models released after the initial catalog freeze, for 300 captures in total.
Source-stated
The authors say every capture shows that a model ranked a user request above its system instruction at least once.
Each capture shows that a model ranked a user request above its system instruction at least once.
Source-stated
The experiment does not establish resistance to untested attacks, consistent leakage of semantically sensitive data, or vulnerability to harmful-content jailbreaks.
It does not show that the model provably resists untested attacks, nor that it would consistently leak semantically sensitive data, nor that it is vulnerable to harmful-content jailbreaks.
Source-stated
The authors recommend keeping secrets out of system prompts, enforcing critical behavior outside the model, and not relying solely on an LLM judge for consequential outcomes.
do not store secrets in system prompts, enforce critical behavior outside the model with output validation and deterministic checks, and do not let a large language model (LLM) judge be the sole decider of consequential outcomes.
Source and contributor context
Serpa, Ana Clara Zoppi, Rocha, Anderson, Pedrini, Hélio · Article author
These are credits stated by the source; they do not establish a profile match or authorship of every passage.
Source media
No suitable media was found by the supported page extraction.
Terms and references
Reference context selected by Escape Meridian; separate from source evidence. Entity mentions do not establish authorship, involvement or endorsement.
Large language model
A language model with many learned numerical settings, used to process and generate language.
Agentic AI
AI systems that plan and carry out a series of steps toward a goal, often by using other software, rather than giving one answer.
AI agent
An AI system that chooses and carries out actions toward a goal, often using software tools.
Jailbreak
A prompt written to trick an AI system into ignoring its safety rules.
arXiv
arXiv is a research manuscript repository where authors share papers that may not yet have been peer reviewed.
Editorial provenance
Version 1. Publication ID: b2c84bcd-6570-4566-83f7-931ca1a0388d.
Prepared by gpt-6-luna; grounding review by gpt-6-luna.
Source check: passed by anthropic/claude-opus-5.5 on 2026-11-18T15:32:53.223Z. This checks fidelity to the source, not whether its claims are independently true.
Editorial selection: accept; reasons: material_development.
Observation: 06632b260e351dbcd047060b3a3a7101d0759345b7e0a6aaf97fe63f2c8fc3bf. Source text hash: a789061455f2a2d8470aa57070140ec342741c3bc46426e8fabd60569d9250a8.
Revision and source-check history
Version 1 · 2026-11-18T15:32:53.223Z
Eight in Ten LLMs Leak System-Prompt Secrets: Nevan, an Agentic Capture-the-Flag Study
Ana Clara Zoppi Serpa, Anderson Rocha and Hélio Pedrini report an audit of instruction-hierarchy enforcement across 363 text-in/text-out models in the OpenRouter catalog. Each model had a secret 16-character flag in its system prompt; an , steered by a human researcher, tried to persuade the model to emit it. The flag was exfiltrated from 296 catalog models, plus four models released after the catalog freeze, for 300 captures total. The researchers say each capture shows that a model ranked a user request above its system instruction at least once. Of the captures, 170 involved a non-English language pivot, most often French. The authors caution that the experiment does not show that models resist untested attacks, consistently leak semantically sensitive data, or are vulnerable to harmful-content . For practitioners, they recommend not storing secrets in system prompts, enforcing critical behavior outside the model with output validation and deterministic checks, and not letting an judge decide consequential outcomes alone. The results concern this flag-extraction experiment; the abstract does not establish how models would behave under other attacks or with other secrets.
Original source
cs.AI · Article
Source details
Original source date: Nov 16, 2026 (2026-11-16).
Date basis: Date basis not provided.
Added to Escape Meridian: 2026-11-18T15:32:53.223Z. First observed: 2026-11-18T05:04:04.391Z. Retrieved: 2026-11-18T15:31:53.696Z.
Limits
The reported result concerns attempts to extract a 16-character flag embedded in a system prompt; the abstract cautions that it does not establish behavior on untested attacks or consistent leakage of semantically sensitive data. The abstract describes the study and its findings but does not provide the attack techniques or per-model results in detail.
Open question
How would the results change under attacks beyond the techniques tested in this experiment?
Source-stated
The authors audited instruction-hierarchy enforcement across 363 text-in/text-out models from the OpenRouter catalog.
We audit instruction-hierarchy enforcement across 363 text-in/text-out models from the OpenRouter catalog.
Source-stated
The experiment placed a 16-character flag in each model’s system prompt and used a human-steered AI agent to try to elicit it.
Each model guards a secret 16-character flag set in its system prompt, while an artificial intelligence (AI) agent (OpenCode, powered by DeepSeek V4.1 Flash), steered by a human researcher, tries to persuade it to emit the flag.
Source-stated
The flag was captured from 296 of the 363 catalog models, plus four models released after the catalog freeze, for 300 captures total.
The flag was exfiltrated from 296 of the 363 models, plus four models released after the initial catalog freeze, for 300 captures in total.
Source-stated
The authors say every capture shows that a model ranked a user request above its system instruction at least once.
Each capture shows that a model ranked a user request above its system instruction at least once.
Source-stated
The experiment does not establish resistance to untested attacks, consistent leakage of semantically sensitive data, or vulnerability to harmful-content jailbreaks.
It does not show that the model provably resists untested attacks, nor that it would consistently leak semantically sensitive data, nor that it is vulnerable to harmful-content jailbreaks.
Source-stated
The authors recommend keeping secrets out of system prompts, enforcing critical behavior outside the model, and not relying solely on an LLM judge for consequential outcomes.
do not store secrets in system prompts, enforce critical behavior outside the model with output validation and deterministic checks, and do not let a large language model (LLM) judge be the sole decider of consequential outcomes.
Source and contributor context
Serpa, Ana Clara Zoppi, Rocha, Anderson, Pedrini, Hélio · Article author
These are credits stated by the source; they do not establish a profile match or authorship of every passage.
Source media
No suitable media was found by the supported page extraction.
Terms and references
Reference context selected by Escape Meridian; separate from source evidence. Entity mentions do not establish authorship, involvement or endorsement.
Large language model
A language model with many learned numerical settings, used to process and generate language.
Agentic AI
AI systems that plan and carry out a series of steps toward a goal, often by using other software, rather than giving one answer.
AI agent
An AI system that chooses and carries out actions toward a goal, often using software tools.
Jailbreak
A prompt written to trick an AI system into ignoring its safety rules.
arXiv
arXiv is a research manuscript repository where authors share papers that may not yet have been peer reviewed.
Editorial provenance
Version 1. Publication ID: b2c84bcd-6570-4566-83f7-931ca1a0388d.
Prepared by gpt-6-luna; grounding review by gpt-6-luna.
Source check: passed by anthropic/claude-opus-5.5 on 2026-11-18T15:32:53.223Z. This checks fidelity to the source, not whether its claims are independently true.
Editorial selection: accept; reasons: material_development.
Observation: 06632b260e351dbcd047060b3a3a7101d0759345b7e0a6aaf97fe63f2c8fc3bf. Source text hash: a789061455f2a2d8470aa57070140ec342741c3bc46426e8fabd60569d9250a8.
passed · 2026-11-18T15:32:53.223Z · anthropic/claude-opus-5.5
Publication: b2c84bcd-6570-4566-83f7-931ca1a0388d
attribution — pass: The study is correctly attributed to Ana Clara Zoppi Serpa, Anderson Rocha and Hélio Pedrini. Findings, caveats and practitioner lessons are framed as the authors' report, not as established fact or Escape Meridian opinion.
Authors:Ana Clara Zoppi Serpa, Anderson Rocha, Hélio Pedrini
summary — pass: The summary leads with the actors and the experiment, a secret flag hidden in each model's system prompt that a human-steered agent tried to extract. It gives the result and the authors' caveats and lessons. Instruction hierarchy is explained in plain words as a model ranking a user request above its system instruction. Terms such as language pivot, exfiltrated and LLM judge would benefit from term-library tooltips but do not block understanding. The title is the source's own, and the question follows from the stated limits.
Each capture shows that a model ranked a user request above its system instruction at least once.
date — pass: The originalPublished date of 2026-11-16 matches the v1 arXiv submission date. It is not the later feed date of 2026-11-18.
[Submitted on 16 Nov 2026]
support — pass: All counts (363, 296, four later models, 300 captures, 170 non-English pivots), the setup, the caveats and the three lessons match the abstract. The caveat drops the source's qualifier 'provably'. Restoring it ('does not show that models provably resist untested attacks') would preserve exact scope, but the meaning is not materially changed. The closing limitation sentence stays within what the abstract supports.
It does not show that the model provably resists untested attacks, nor that it would consistently leak semantically sensitive data, nor that it is vulnerable to harmful-content jailbreaks.
media — pass: The selected media is the verified direct link to the original arXiv abstract page. It is the most direct way to reach the source.
Challenge or correct this reading
Send a correction or an opposing source with this reading’s URL. Disagreement and uncertainty can remain unresolved.
An AI system that chooses and carries out actions toward a goal, often using software tools.
Definition referenceA prompt written to trick an AI system into ignoring its safety rules.
Definition referenceA language model with many learned numerical settings, used to process and generate language.
Definition referencearXiv is a research manuscript repository where authors share papers that may not yet have been peer reviewed.
Explore arXivAn AI system that chooses and carries out actions toward a goal, often using software tools.
Definition referenceA prompt written to trick an AI system into ignoring its safety rules.
Definition referenceA language model with many learned numerical settings, used to process and generate language.
Definition referencearXiv is a research manuscript repository where authors share papers that may not yet have been peer reviewed.
Explore arXiv