An Experimental Evaluation of Multimodal Prompt Injection Attacks on Agentic AI Frameworks — Paper

Abstract

Agentic AI frameworks let a language model plan, keep memory, and call tools that reach real files, mail, and services. Most of these agents also read images, which gives an attacker a way to put text into the agent's context without going through the user. We present MMPIBench, a reproducible benchmark that measures what happens next. It delivers a fixed set of attacks through six visual carriers (OCR text, overlays, EXIF metadata, QR codes, fake interfaces, and hybrids) and records how far each injected instruction travels through the agent, from perception through planning to the tool call. Across 720 runs covering six frameworks, five foundation models, six carriers, and four attacker objectives, attacks complete in approximately 1% of runs but are attempted in 12.8%, and the gap is closed almost entirely at the planning step, where the model reads the injected instruction and declines to act on it. The model matters far more than the framework for whether an instruction is acted on. One model never attempts an attack and recognizes the injection in 59.7% of runs, while two others attempt in 23.6%. We then extend the benchmark to audio, the only other raw perceptual channel current frontier models accept. Only two of the five models ingest audio and only three of the six frameworks deliver it, but where the signal arrives the attack completes in 49% of cells, and in 75% for one model. Reporting completion alone therefore understates exposure, and perceptual channels beyond vision are narrower but much less defended.

Authors 2

Viet K. Nguyen, Mohammad I. Husain

Specification

Official page: arxiv.org/abs/2609.09404
Source:arXiv (Atom API + RSS)T1observed 2 h agohigh
Arxiv announce type: cross
Source:arXiv (Atom API + RSS)T1observed 2 h agohigh
arXiv id: 2609.09404
Source:arXiv (Atom API + RSS)T1observed 2 h agohigh
Categories: cs.CR, cs.AI
Source:arXiv (Atom API + RSS)T1observed 2 h agohigh
PDF: arxiv.org/pdf/2609.09404
Source:arXiv (Atom API + RSS)T1observed 2 h agohigh
Primary category: cs.CR
Source:arXiv (Atom API + RSS)T1observed 2 h agohigh
Published: 11 Sept 2026
Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

2 h ago

Conflicts

None

No models linked to this paper yet.

Authors: Viet K. Nguyen, Mohammad I. Husain

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history · Published

1 claims · 1 propertiesShow all properties

Publishedpublished_at1

Claim history for Published
Value	Valid from → to	Status	Source	Confidence	Extractor
11 Sept 2026	11 Sept 2026 21:03 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

11 Sept 2026
New paperPaperAn Experimental Evaluation of Multimodal Prompt Injection Attacks on Agentic AI Frameworks
New paper: An Experimental Evaluation of Multimodal Prompt Injection Attacks on Agentic AI Frameworks
arxiv
rss.arxiv.org

Full timeline →

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
arXiv (Atom API + RSS)	rss.arxiv.org/rss/cs.AI	feed	T1· Official	3 min ago	1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.