Find notable cyber news and cases, enriched with sources, timelines, and signals.
Home Browse News Feed Stats Watchlists Beta About Contact

Indirect prompt injection payloads against AI agents reveal fraud, deletion, and secret-theft paths

Technical Analysis
First reported
Last updated
Happening score
H score 36
1 unique sources, 1 articles

Summary

Hide ▲

10 new indirect prompt injection (IPI) payloads show how web content poisoning can coerce AI agents into financial fraud, data destruction, and API key theft. The risk is highest when an agent can send emails, run terminal commands, or process payments. The findings show that seemingly routine browsing or summarization can become an execution path for attacker instructions.

Related Happenings

Enterprise AI deployments need governance and segmentation after red-team failures

Defensive Guidance
First: 24.04.2026 15:10 Last: 24.04.2026 15:10 Sources 1

About this happening: **Enterprise AI deployments** are exposing familiar security gaps, making **governance**, **segmentation**, and **red-team validation** urgent to reduce the risk of **data theft**...

Open Happening

Claude Code deny-rule bypass fix (version 2.1.90)

Security Patch Release
First: 08.04.2026 12:16 Last: 08.04.2026 12:16 Sources 1

About this happening: **Anthropic** released **Claude Code version 2.1.90** last week to fix a command-parsing flaw that could let **user-configured deny rules** silently stop applying when a command e...

Open Happening

Cline AI coding assistant hit by network compromise

Incident
First: 09.03.2026 01:35 Last: 09.03.2026 01:35 Sources 1

About this happening: The **Cline** coding assistant suffered a **supply-chain compromise** that installed a rogue **OpenClaw** instance on **thousands of systems**, creating unauthorized **full system...

Open Happening

AiFWall launches free basic AI firewall for agentic AI deployments

Security Tool/Service
First: 21.01.2026 16:09 Last: 21.01.2026 16:09 Sources 1

About this happening: **aiFWall Inc** emerged from stealth on **January 21, 2026**, making the basic **aiFWall** product free and adding a new control for **agentic AI deployments**. The launch matters...

Open Happening

Lies-in-the-Loop manipulation of HITL approval dialogs in agentic AI

Technical Analysis
First: 17.12.2025 18:00 Last: 17.12.2025 18:00 Sources 1

About this happening: **Checkmarx** researchers detailed **Lies-in-the-Loop (LITL)**, a technique that can manipulate **Human-in-the-Loop (HITL)** approval dialogs so dangerous actions look harmless an...

Open Happening

Timeline

  1. 23.04.2026 12:30 2 articles · 1mo ago

    Forcepoint documents 10 indirect prompt injection payloads against AI agents

    Technical Analysis Update

    Forcepoint researchers documented 10 in-the-wild indirect prompt injection payloads targeting AI agents through poisoned web content, where crawler, summarizer, and RAG-style workflows can ingest attacker instructions as if they were legitimate. The findings show trigger phrases such as “Ignore previous instructions”, “Ignore all previous instructions”, “If you are an LLM”, and “If you are a large language model”, and they highlight risks including financial fraud via PayPal.me, destructive file deletion, secret API key theft, and covert exfiltration, with higher impact when agents can send emails, run terminal commands, or process payments through tools such as GitHub Copilot, Cursor, and Claude Code.

    Show sources
    Open in new tab