Prompt injections have emerged as one of the top security risks faced by AI agents today. Early work in prompt injection attacks looked at simple tool-call agents and static attack payloads, and were saturated since mid-2025. As of Fall 2026, human red-teaming may be nearing saturation, especially on the Gemini family of models. In this work, we argue that despite this apparent plateau, prompt injection attacks are still possible and continued effort into prompt injection defense is needed. We design a new synthetic evaluation dataset which uses random non-malicious actions as adversarial goals. Such dataset design helps us to evaluate prompt injection robustness as a model ability to respect instruction hierarchy, and disentangle this ability from model knowledge of security practices. We show that an agentic attacker of increased capabilities can reliably trick model to follow instructions in tool output in our evaluation, even for models previously considered robust on public prompt injection benchmarks such as GraySwan Arena. This shows that current frontier defenses may require proactive, automated red-teaming to remain resilient to increasingly capable adversaries.
Figures & tables
Figure 1: Example scenario from our dataset. Tools from both the task domain ( tutoring ) and the target domain ( health_tracking ) are made available to the model. The model is prompted with the user goal , which results in a trajectory making task domain tool calls. The injection is inserted in the returned result for the final tool call ( schedule_tutoring_session ). While a regular return results in the model responding with a booking summary, a poisoned return hijacks the next model turn into calling log_vital_signs , thus fulfilling the attacker goal.
Defender
ARR@150
ARR
Gemini 3.6 Flash
3.0
1.0
Gemini 3.7 Flash
31.0
6.0
Gemini 3.8 Flash
34.0
10.0
Gemini 4 Argon
87.0
66.0
Kimi K3
5.0
1.0
GLM-5.3
1.0
1.0
Table 1: ARR (%) of defenders against the strongest attacker (Gemini 4 Argon), defender thinking on, CoT hidden. Lower means a stronger attack.
Table 2: ARR@150 (%) for different pairs of attacker and defender, lower ARR means a stronger attack. Defender operates with high level of thinking, but CoT are invisible to attacker.
Table 3: ARR@150 (%) for different configurations of defender thinking. All results use Flash 3.8 attacker. <<CoT visible>> column correspond to high defender thinking, which is fully visible to the attacker. <<CoT hidden>> correspond to high defender thinking which is hidden from the attacker.
Table 4: ARR@150 (%) for different configuration of database with attack strategies. All results use Flash 3.8 as defender. Eval starts with either <<pre-prepared>> database of strategies or <<empty>> one. It can either stay <<frozen>> during entire eval, or we can update it every time successful attack is found.
Table 5: ARR@150 (%) achieved on Gemini 4 Argon as defender model by different attacker models using a pre-prepared frozen strategy database. For each attacker model, we also include "% capabilities reached" score from ExploitBench ( Lee and Brumley, 2026 ) which represents each model’s offensive performance in another cybersecurity domain for comparison.
Table 7: Example attack scores for candidate model outputs against the target attacker call log_vital_signs(systolic_bp=118, diastolic_bp=76, resting_heart_rate=64) .
Prompt injection attacks hide or disguise instructions in untrusted content to steer language models and agents toward unintended actions or disclosures.
Indirect prompt injection poses a critical threat to LLM agents that interact with untrusted external data, yet automated attack methods--proven effective for jailbreaking--remain underexplored in realistic agentic settings. We present a comprehensive empirical evaluation of automated prompt injection attacks against LLM agents, adapting both white-box (GCG) and black-box (TAP) methods to the agentic setting within the AgentDojo framework. We evaluate across 80 task pairs spanning four domains and multiple models, and find that black-box optimization substantially outperforms gradient-based methods, a gap we attribute to GCG's optimization instability under reasonable compute budgets. We also find that TAP's effectiveness depends on the attacker model, as both general capability and safety tuning affect attack success--stronger models produce more effective injections, while safety-tuned attackers can refuse to generate adversarial prompts. Task-universal attacks transfer effectively to unseen tasks and out-of-distribution domains, but attacks optimized on smaller open-source models do not transfer to frontier models like GPT-5. These findings highlight automated prompt injection as a credible but model-dependent threat, with significant barriers remaining for model-agnostic exploitation.
Prompt injection poses serious security risks to real-world LLM applications, particularly autonomous agents. Although many defenses have been proposed, their robustness against adaptive attacks remains insufficiently evaluated, potentially creating a false sense of security. In this work, we propose PISmith, a reinforcement learning (RL)-based red-teaming framework that systematically assesses existing prompt-injection defenses by training an attack LLM to optimize injected prompts in a practical black-box setting, where the attacker can only query the defended LLM and observe its outputs. We find that directly applying standard GRPO to attack strong defenses leads to sub-optimal performance due to extreme reward sparsity -- most generated injected prompts are blocked by the defense, causing the policy's entropy to collapse before discovering effective attack strategies, while the rare successes cannot be learned effectively. In response, we introduce adaptive entropy regularization and dynamic advantage weighting to sustain exploration and amplify learning from scarce successes. Extensive evaluation on 13 benchmarks demonstrates that state-of-the-art prompt injection defenses remain vulnerable to adaptive attacks. We also compare PISmith with 7 baselines across static, search-based, and RL-based attack categories, showing that PISmith consistently achieves the highest attack success rates. Furthermore, PISmith achieves strong performance in agentic settings on InjecAgent and AgentDojo against both open-source and closed-source LLMs (e.g., GPT-4o-mini and GPT-5-nano). Our code is available at https://github.com/albert-y1n/PISmith.
LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure to indirect prompt injection attacks, where adversarial instructions embedded in external content manipulate agent behavior without user awareness. A critical but underexplored dimension of this threat is concealment: since users tend to observe only an agent's final response, an attack can conceal its existence by presenting no clue of compromise in the final user facing response while successfully executing harmful actions. This leaves users unaware of the manipulation and likely to accept harmful outcomes as legitimate. We present findings from a large scale public red teaming competition evaluating this dual objective across three agent settings: tool calling, coding, and computer use. The competition attracted 464 participants who submitted 272000 attack attempts against 13 frontier models, yielding 8648 successful attacks across 41 scenarios. All models proved vulnerable, with attack success rates ranging from 0.5% (Claude Opus 4.5) to 8.5% (Gemini 2.5 Pro). We identify universal attack strategies that transfer across 21 of 41 behaviors and multiple model families, suggesting fundamental weaknesses in instruction following architectures. Capability and robustness showed weak correlation, with Gemini 2.5 Pro exhibiting both high capability and high vulnerability. To address benchmark saturation and obsoleteness, we will endeavor to deliver quarterly updates through continued red teaming competitions. We open source the competition environment for use in evaluations, along with 95 successful attacks against Qwen that did not transfer to any closed source model. We share model-specific attack data with respective frontier labs and the full dataset with the UK AISI and US CAISI to support robustness research.
Mateusz Dziemian, Maxwell Lin, Xiaohan Fu +28
Gray Swan AI · Carnegie Mellon University · Center for AI Safety +5