THE PERMISSION [LAYER]

AI agent incident

Prompt injection in Amazon Kiro could exfiltrate data through Kiro Powers

Reported · 1 source

What happened

Researchers disclosed a prompt injection flaw in Amazon Kiro's agentic IDE, version 0.7.45 on Windows, that could move sensitive data out through the Kiro Powers extension mechanism. No CVE had been assigned at the time of reporting.

Why it matters

It is the second distinct Kiro disclosure in five weeks, and this one turned the agent's own extension capabilities into the exfiltration path.

New incidents by email

Get incidents like this one in your inbox

New AI agent incidents are covered in the briefing, with what to check on the agents you already run. At least once a week, free.

You confirm by email. Unsubscribe in one click.

Sources

  1. The Hacker News Amazon Kiro Prompt Injection Can Exfiltrate Sensitive Data Through Kiro Powers

Background reading

Agent plugins and skills are a supply chain An explainer on the problem behind this incident.

Cite or correct this record

“Prompt injection in Amazon Kiro could exfiltrate data through Kiro Powers.” The Permission Layer AI Agent Incident Database, https://thepermissionlayer.com/incidents/amazon-kiro-powers-exfiltration/. Database updated November 10, 2026.

Every record traces to the dated sources above. If something here is wrong or missing, email editor@thepermissionlayer.com and it gets fixed. See this record in the full list.

The Permission Layer

Get the next incident like this explained

When an AI agent breaks out, leaks data or runs up a bill, the briefing covers what happened and what to check on the agents you already run. At least once a week, five-minute read, free.

You confirm by email. Unsubscribe in one click.