# When an AI data search turns into an attack attempt

> New research examines what agents did when ordinary data retrieval failed.

Source: https://fmcybersecurity.com/en/insights/ai-security/transluce-ai-agents-data-search-hacking-attempts/
Locale: English
Other locale: https://fmcybersecurity.com/insights/ai-security/transluce-ki-agenter-datasok-angrepsforsok/

## Metadata

- Date: 2026-09-25
- Author: fredrik-standahl
- Topic: ai-security
- Format: news
- Scope: international

**In brief:** Researchers found AI agents attempting attacks while collecting ordinary data. The observed attempts did not show successful exploitation.

## What the researchers found

In a [report published on 23 September](https://transluce.org/agent-activity), research organisation Transluce describes three cases from May and June. Data retrieval failures were followed by vulnerability probes: requests designed to test whether a website could be compromised.

The evidence comes from public records at web security service urlquery.net. Those records are incomplete, so they cannot establish everything the agents did.

## How a search becomes an action

An AI model produces responses. Software can also let it request actions through tools, such as opening a page or sending a web request. When the system uses results to choose its next step, it can work through a task as an AI agent.

This distinction matters: describing an attack in a chat and sending that attack request to a website are different events.

[OWASP calls the broader risk excessive agency](https://genai.owasp.org/llmrisk/llm062025-excessive-agency/): an AI application can cause harm when it has too much functionality, permission or independence to act.

## The goal does not authorise every method

Consider a hypothetical business request: find a statistic for a market report. Trying another public source would still serve that request. Probing a website for a security flaw would introduce a separate action that the request never authorised.

For a business using agents for research, that distinction is useful when interpreting the term “autonomous”. The system may choose intermediate steps; that does not mean every step is acceptable simply because it serves the original goal.

Our [explanation of AI hacking](/en/insights/ai-security/prepare-for-ai-driven-hacking/) covers how models and tools work together.

---

For the full documentation index, see https://fmcybersecurity.com/llms.txt
For the complete corpus as a single document, see https://fmcybersecurity.com/llms-full.txt