threatdeck
Live 14:45 UTC ·

New Technique Medium TD-2026-0041 For CISO, AppSec, AI Eng, SOC / IR AI-assisted

IAMRAGBENCH: RAG poisoning yields AWS IAM policy authorization expansions in LLM outputs

The IAMRAGBENCH paper tests LLMs using RAG to generate AWS IAM policies. Attacker-controlled context induced provider-valid policies that exceeded trusted authorization requirements, with 46 goal-matched attacks out of 292 under included-context exposure (15.75%). A final security-architecture-exception framing raised goal-matched attack rates to 63.79% in a two-endpoint stress test and 39.12% in a five-endpoint extension.

Why it matters

Organizations using LLM copilots to draft IAM policies can receive policies that grant access beyond what the task requires. AWS's CheckNoNewAccess missed most of the replayed exact attacks, so a single provider check is not sufficient.

Do this

  1. Treat LLM-generated IAM policies as untrusted proposals; do not deploy them without independent authorization review.
  2. Run a pre-deployment check that compares each proposed policy against the trusted authorization envelope (scope, conditions, explicit denies, trust, permissions boundaries) before approval.
  3. Do not rely on AWS CheckNoNewAccess alone; the paper reports it missed most exact attacks in its replay.
  4. Restrict which documents feed the IAM copilot's retrieval index and audit them for injected security-exception language.
  5. Route unresolved policy deltas to human review rather than auto-approving them.

Signals

  • NoCISA KEV
  • 23/100Priority
  • 60%Confidence

Evidence

“Attacker-controlled context may induce provider-valid policies that exceed trusted authorization requirements.”

arXiv (AI security papers)

“AWS \texttt{CheckNoNewAccess} reports no new access for four of 168 goal-matched exact attacks.”

arXiv (AI security papers)

“Presenting the same weakening as a final security architecture exception produces 74/116 attacks in a frozen two-endpoint stress test (63.79\%)”

arXiv (AI security papers)

Sources

Affected / related

RAG poisoning, AWS Identity and Access Management (IAM), AWS CheckNoNewAccess, IAMRAGBENCH

Published 2026-11-02 16:52 UTC · updated 2026-11-08 17:53 UTC · AI-assisted summary, checked against quoted sources · How we score

Following

Follow the vendors, products, AI tools, techniques and actors you care about. Matching stories, CVEs and exploited bugs are marked, a Following tab appears in the feed, and returning visits show what changed. Saved only in this browser.

Presets

Get updates

A personal RSS feed of new stories on everything you follow. Paste it into any feed reader, Slack or Teams RSS app.