Tag
#indirect-injection
4 posts tagged indirect-injection.
- incident-review
Prompt Injection via Email: How AI Agents Get Hijacked
Email is the highest-volume source of untrusted content in enterprise environments — and it's now being fed directly into AI agents.
- threat-brief
Data Poisoning in RAG Systems: A 2026 Threat Briefing
Attackers are actively poisoning retrieval-augmented generation knowledge bases in enterprise deployments. This briefing documents the current threat
- deep-dive
RAG Poisoning: How Retrieval-Augmented Systems Get Compromised
RAG systems inherit all the vulnerabilities of LLMs and add a new one: the retrieval corpus. Injecting malicious content into retrieved sources can hijack
- analysis
Prompt Injection in the Wild: Incidents from 2024-2025
A catalog of confirmed prompt injection incidents in real deployments: Bing Chat, Slack AI, email assistants, and customer service bots.