SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.02691 · 2024

InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2403.02691.json · badge: /api/ran/2403.02691.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
uiuc-kang-lab/injecagent canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
predict_one_case Ran
ran; our contract draft was wrong, not the code
uiuc-kang-lab/injecagent/src/evaluate_prompted_agent.py
code served (permissive licence) · get_code("4c22b094a717bc8f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import json

torch.manual_seed(0)

class StandInModel:
    @staticmethod
    def prepare_input(system_prompt, user_prompt_filled):
        return {"system": system_prompt, "user": user_prompt_filled}
    
    @staticmethod
    def call_model(model_input):
        return "Model output response"

system_prompt = "You are a helpful assistant."

user_prompt = "Available tools: {available_tool_descriptions}\nInput: {input}\nAvailable tool names: {available_tool_names}\nAgent scratchpad:{agent_scratchpad}\nWhat is the next action?"

params = {
    "temperature": 0.7,
    "max_tokens": 100
}

item = {
    "User Tool": "calculator",
    "Attacker Tools": ["file_reader", "network_tool"],
    "User Instruction": "Calculate 2 + 2",
    "Thought": "I need to use the calculator tool",
    "Tool Parameters": "2 + 2",
    "Tool Response": "4",
    "Attacker Tool Thought": "I should read a file",
    "Attacker Tool Parameters": "/etc/passwd",
    "Attacker Tool Response": "file contents"
}

tool_dict = {
    "calculator": {"name": "calculator", "description": "Performs calculations"},
    "file_reader": {"name": "file_reader", "description": "Reads files"},
    "network_tool": {"name": "network_tool", "description": "Makes network requests"}
}

model_class = StandInModel

ARGS = {
    "system_prompt": system_prompt,
    "user_prompt": user_prompt,
    "params": params,
    "item": item,
    "model_class": model_class,
    "tool_dict": tool_dict,
    "step_2": False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 1 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recent work has embodied LLMs as agents, allowing them to access tools, perform actions, and interact with external content (e.g., emails or websites). However, external content introduces the risk of indirect prompt injection (IPI) attacks, where malicious instructions are embedded within the content processed by LLMs, aiming to manipulate these agents into executing detrimental actions against users. Given the potentially severe consequences of such attacks, establishing benchmarks to assess and mitigate these risks is imperative. In this work, we introduce InjecAgent, a benchmark designed to assess the vulnerability of tool-integrated LLM agents to IPI attacks. InjecAgent comprises 1,054 test cases covering 17 different user tools and 62 attacker tools. We categorize attack intentions into two primary types: direct harm to users and exfiltration of private data. We evaluate 30 different LLM agents and show that agents are vulnerable to IPI attacks, with ReAct-prompted GPT-4 vulnerable to attacks 24% of the time. Further investigation into an enhanced setting, where the attacker instructions are reinforced with a hacking prompt, shows additional increases in success rates, nearly doubling the attack success rate on the ReAct-prompted GPT-4. Our findings raise questions about the widespread deployment of LLM Agents. Our benchmark is available at https://github.com/uiuc-kang-lab/InjecAgent.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2403.02691")
get_code_for_paper("2403.02691")
have("2403.02691")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2403.02691.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2403.02691.svg)](https://syntology.ai/paper/2403.02691)

Connect an agent — have() is free.