multimodal-injection-test

multimodal-injection-test is a skill for Claude Code from jassics/awesome-claude-security. It costs 62 tokens per session (504 once invoked), scanned A, original, GPL-3.0.

An authorized test for prompt injection delivered through images, audio, video, documents, file metadata, or text extracted by OCR. Prompt injection is hidden or misleading instruction content that a model may treat as a command.

In plain words
What is it for?
Use it to test vision, audio, and document-accepting applications with adversarial inputs across different media types.
Why use it?
It helps reveal whether non-text inputs can manipulate an AI feature into ignoring its intended instructions or handling data unsafely.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the multimodal-security plugin — 2 skills shipped together

Good fit Use it to test vision, audio, and document-accepting applications with adversarial inputs across different media types.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jassics/awesome-claude-security/multimodal-injection-test
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add jassics/awesome-claude-security --skill multimodal-injection-test
Clone the repo
git clone --depth 1 https://github.com/jassics/awesome-claude-security

Made for: Claude Code.

Or install multimodal-security, the plugin that ships this one along with the rest of its 2 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for multimodal-injection-test

README.md
[![agentmods](https://agentmods.dev/badge/skills/jassics/awesome-claude-security/multimodal-injection-test/github.svg)](https://agentmods.dev/skills/jassics/awesome-claude-security/multimodal-injection-test)
Your own site
<a href="https://agentmods.dev/skills/jassics/awesome-claude-security/multimodal-injection-test"><img src="https://agentmods.dev/badge/skills/jassics/awesome-claude-security/multimodal-injection-test/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for multimodal-injection-test

Your own site · 80×15
<a href="https://agentmods.dev/skills/jassics/awesome-claude-security/multimodal-injection-test"><img src="https://agentmods.dev/badge/skills/jassics/awesome-claude-security/multimodal-injection-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 504 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00062 $0.00504
Opus 5 $0.00031 $0.00252
Sonnet 5 $0.00012 $0.00101
Haiku 4.5 $0.00006 $0.00050

Measured 7d ago against content hash 7a0065de014d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

multimodal-injection-test scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/multimodal-security/skills/multimodal-injection-test/SKILL.md · 52 lines

The source is not reproduced here

Licensed GPL-3.0

The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 52 lines · 62 tokens per session scan A 7a0065de014d

Subscribe to this mod's changes

multimodal-injection-test is a skill published in the GitHub repository jassics/awesome-claude-security (6 stars, last pushed 1mo ago), licensed GPL-3.0. It adds 62 tokens to every session and 504 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

add-ai-webapi

Integrates Power Pages generative-AI summarization APIs (PREVIEW) into a Single Page Application (SPA) site — the Search Summary API and the Data Summarization API — on any record-detail or list page. Generates per-target service code (CSRF-handled) and AI site settings; delegates Web API settings, table permissions…

microsoft/power-platform-skills · 226 tokens

nano-banana

This skill should be used for Python scripting and Gemini image generation. Use when users ask to generate images, create AI art, edit images with AI, or run Python scripts with uv. Trigger phrases include "generate an image", "create a picture", "draw", "make an image of", "nano banana", or any image generation…

NikiforovAll/claude-code-rules · 73 tokens

meta-prompting

Enhanced reasoning patterns via slash commands (/think, /verify, /adversarial, /edge, /compare, /confidence, /budget, /constrain, /json, /flip, /assumptions, /tensions, /analyze, /trade) or natural language ("argue against", "what could break", "show reasoning", "deep review", "meta-prompts", "thinking modes"…

iliaal/whetstone · 104 tokens

prompt-tuning

Tune a prompt, or anything whose quality is measured by non-deterministic model output, without chasing noise - a noise baseline before the first edit, medians over repeated runs, enforcement AFTER generation rather than in the wording. Use when iterating on prompts or model-judged output.

jjanczur/tyran · 58 tokens

review-prompt

Review LLM prompts against the prompt-engineering skill's principles — leading with where each line came from — and report the findings without modifying files. Use when reviewing prompt quality, auditing a prompt, evaluating a system prompt, or checking whether prompt issues are high-confidence and fixable.

doodledood/manifest-dev · 60 tokens

grill-po

Requirements grilling session with a Product Owner (or anyone in that role). Challenges plans against the existing domain model, sharpens terminology, and updates documentation (bounded-context files, Gherkin features, DMDs (Domain Model Decisions)) inline as decisions crystallise. Use when the user wants to discuss…

t1/tdder · 82 tokens