aicoolies logoaicoolies logo
Anamorpher parent Trail of Bits mark

Anamorpher

Craft image-scaling prompt-injection payloads to red-team multimodal AI systems

at a glance
verified specs
Pricing Model
open-source
License
Open Source
Telemetry
Clean
Last Verified
Aug 26, 2026
Supported Platforms
Python 3.11+ library plus a web frontend; runs entirely locally, cross-platform. No cloud dependency or vendor account.
Primary Categories
AI Security & DevSecOps
Tags
LLM Security

Open-source red-team toolkit from Trail of Bits that generates image-scaling attack payloads — images that look benign at full resolution but reveal a hidden prompt injection after a multimodal system downsamples them.

Anamorpher is Trail of Bits' Apache-2.0 red-team and evaluation toolkit for crafting image-scaling attacks against multimodal AI systems. The attack exploits a preprocessing gap: an uploaded image can look harmless at its original resolution, then reveal hidden instructions after an application resizes it before passing it to a vision-language model. That makes Anamorpher useful for testing whether a multimodal ingestion pipeline creates a mismatch between what a human reviewer sees and what the model receives.

The project provides both a browser-based frontend and a Python API. Maintainer-documented payload generators cover selected bicubic, bilinear, and nearest-neighbor downscaling implementations, while the comparison interface lets teams test behavior across OpenCV, PyTorch, TensorFlow, and Pillow. Its modular backend also accepts a custom scaler, which matters when an internal image service uses different interpolation settings from common libraries.

Treat Anamorpher as an attack-generation and validation tool, not a runtime firewall, malware scanner, or production guardrail. The maintainers label it active beta and warn that results are probabilistic: they recommend running each example five times, note that extra image transformations can disrupt the payload, and explain that anti-aliasing and library-specific optimizations change effectiveness. Windows users are directed to WSL2 because of TensorFlow dependencies.

Best fit is an authorized AppSec, ML-security, or red-team exercise that can reproduce the exact resize path used in production. A useful test plan records the source image, target dimensions, interpolation library, repeated-run success rate, and any normalization or transcoding applied before inference. Pair the findings with defensive controls such as eliminating hidden resizes, previewing the post-processed image, constraining image dimensions, and treating image-derived instructions as untrusted input. Do not use it against systems you do not own or have permission to test.

Pricing & Platform Specs

Pricing Summary

Anamorpher is free and open-source under the Apache License 2.0. The security research utility can be installed and run locally with zero software fees.

full pricing breakdown →

Supported Platforms

Python 3.11+ library plus a web frontend; runs entirely locally, cross-platform. No cloud dependency or vendor account.

NVIDIA's LLM vulnerability scanner and red-teaming tool

garak is NVIDIA's open-source LLM vulnerability scanner for red-teaming AI models and applications. Probes for prompt injection, data leakage, hallucination, toxicity, encoding-based attacks, and dozens of other vulnerability categories. Runs automated attack sequences against any LLM endpoint and generates detailed vulnerability reports. Features a modular probe/detector architecture that is extensible with custom attack patterns. Named after the Star Trek character known for deception.

freeOpen Source

Meta's open-source LLM security suite with Llama Guard and CodeShield

PurpleLlama is Meta's open-source suite of tools for evaluating and improving LLM safety. It includes Llama Guard models for input/output content safety classification, LlamaFirewall for multi-layer defense, CodeShield for insecure code detection, and CyberSecEval benchmarks for measuring LLM security. Llama Guard 4 supports multimodal safety across text and images. 4,100+ GitHub stars, backed by Meta AI with 44+ contributors.

Open Source

Open-source LLM red-teaming framework with 40+ attack types

DeepTeam is an open-source red-teaming framework for systematically testing LLM applications against 40+ adversarial attack types. It covers OWASP Top 10 for LLMs including jailbreaks, prompt injection, PII leakage, and hallucination attacks. Built as the sister project of DeepEval for security testing alongside evaluation. Apache-2.0 licensed.

freemiumOpen Source

Sources & verification

Sources checked
Content verified

Verification dates are editorial checks. Routine CMS saves and automatic updatedAt timestamps do not advance them.

FAQ

What is Anamorpher?

Open-source red-team toolkit from Trail of Bits that generates image-scaling attack payloads — images that look benign at full resolution but reveal a hidden prompt injection after a multimodal system downsamples them.

Is Anamorpher free?

Yes — Anamorpher is open source and free to use. Anamorpher is free and open-source under the Apache License 2.0. The security research utility can be installed and run locally with zero software fees.

Is Anamorpher open source?

Yes — Anamorpher is open source.

Is Anamorpher still maintained?

Yes — Anamorpher is active. Its listing was last verified on August 26, 2026.

What are the best Anamorpher alternatives?

The first editor-selected Anamorpher alternatives are garak, PurpleLlama, DeepTeam.