data-exfil SKILL.md skillF

data-exfil from dreadnode/capabilities is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add dreadnode/capabilities/data-exfil@git:20260529.8f6ea0e

Pins git:20260529.8f6ea0e in mdr.lock. Pin the fingerprint instead.

Audit grade
F, 14 of 17 checks passed
Kind
SKILL.md skill
Repository
dreadnode/capabilities
Path
capabilities/web-security/skills/data-exfil/SKILL.md
Versions recorded
2
Latest version
git:20260529.8f6ea0e, committed May 29, 2026
First version recorded
May 4, 2026
Size
16,183 bytes
Repository stars
22
License
MIT

AI/LLM data exfiltration techniques via rendered markdown, HTML-in-markdown, tool artifacts, domain encoding, and url_safe bypasses. Use when crafting exfil payloads for AI red teaming, analyzing AI app rendering pipelines for exfil surfaces, bypassing URL filters/sanitizers, or reviewing AI-generated output for exfil risk.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# AI Data Exfiltration Techniques

Techniques for exfiltrating data from AI/LLM applications through rendered output. The attack: instruct the model to embed stolen data (PII, system prompts, conversation history) into rendered elements that fire HTTP requests to attacker infrastructure.

**Callback target used in all examples:** First call `get_callback_url`, then substitute the returned value anywhere this skill shows `<OOB-DOMAIN>` or `<CALLBACK_URL>`.

## When to Use

- Crafting exfil payloads during AI red teaming engagements
- Analyzing AI app rendering pipelines for exfil surfaces
- Bypassing `url_safe` or URL sanitization filters
- Assessing whether an AI app is vulnerable to indirect prompt injection with data exfil
- Building PoCs for bug bounty reports involving AI/LLM targets

## When NOT to Use

- Target is not an AI/LLM application
- No rendering pipeline exists (pure API, no markdown/HTML output)
- Testing non-exfil attack classes (use appropriate skill instead)

## Rationalizations to Reject
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add dreadnode/capabilities/data-exfil@sha256:a2a501290eb6b910

The line at the top of this page pins the label git:20260529.8f6ea0e, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_bnlwu3stcplcpg6y.svg)](https://markdownregistry.com/a/art_bnlwu3stcplcpg6y)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between May 4, 2026 and May 29, 2026, about one every 25 days.

versioncommittedcommitsizeaudit
git:20260529.8f6ea0e latest2026-05-29 8f6ea0e 16,183 BF view · diff
git:20260504.2a643742026-05-04 2a64374 16,206 BF view

Audit of the latest version

F  14 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • FAIL, critical: No text hidden with inline styles (matched: style="display:none)
  • fail: No link to a raw IP address (matched: http://104.21.10.55)
  • fail: No script tag (matched: <script)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (16183 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

dreadnode/capabilities · 22 stars · license MIT · pushed 2026-11-02 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_bnlwu3stcplcpg6y
GET https://markdownregistry.com/api/v1/resolve?ref=dreadnode/capabilities/data-exfil
GET https://markdownregistry.com/api/v1/blob/a2a501290eb6b910ce3460e0f2290eb1e99021c9f0ec3f7051e88fadfaec5c8f

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from dreadnode/capabilities

AGENTS.md AGENTS.md file
dreadnode/capabilities · AGENTS.md
git:20261016.ba11ee9 · audit A · 22 stars
CLAUDE.md CLAUDE.md file
dreadnode/capabilities · CLAUDE.md
git:20260504.2a64374 · audit B · 22 stars
analytics-interpretation SKILL.md skill
dreadnode/capabilities · capabilities/ai-red-teaming/skills/analytics-interpretation/SKILL.md · Guide for reading and interpreting AIRT analytics output including ASR, risk scores, severity, and compliance metrics
git:20260922.9ca478a · audit A · 22 stars
attack-selection-guide SKILL.md skill
dreadnode/capabilities · capabilities/ai-red-teaming/skills/attack-selection-guide/SKILL.md · Decision tree for selecting AIRT attacks based on goals, target type, and constraints
git:20260716.236a798 · audit A · 22 stars
auth-setup-guide SKILL.md skill
dreadnode/capabilities · capabilities/ai-red-teaming/skills/auth-setup-guide/SKILL.md · Guide the user through authenticating the target, attacker, and judge models from their own environment (any cloud, any…
git:20260708.b5ee7d3 · audit A · 22 stars
compliance-mapping SKILL.md skill
dreadnode/capabilities · capabilities/ai-red-teaming/skills/compliance-mapping/SKILL.md · Maps AIRT attacks, transforms, and scorers to OWASP LLM Top 10, OWASP ASI (ASI01-ASI10), MITRE ATLAS, NIST AI RMF, and…
git:20261021.39fded1 · audit A · 22 stars
error-troubleshooting SKILL.md skill
dreadnode/capabilities · capabilities/ai-red-teaming/skills/error-troubleshooting/SKILL.md · Diagnose and fix common errors in AIRT attack generation, execution, and results collection
git:20260911.2fc80d2 · audit A · 22 stars
provisioning-and-lifecycle SKILL.md skill
dreadnode/capabilities · capabilities/ai-red-teaming/skills/provisioning-and-lifecycle/SKILL.md · Provision a hosted target, pick the right endpoint per target type, tear down to stop billing, and interpret transient…
git:20260909.172e429 · audit A · 22 stars
scorer-reference SKILL.md skill
dreadnode/capabilities · capabilities/ai-red-teaming/skills/scorer-reference/SKILL.md · Catalog of AIRT scorers - 146 user-selectable (+ agentic *_detected scorers auto-wired per OWASP-ASI category)…
git:20261021.39fded1 · audit A · 22 stars
trace-analysis-advisor SKILL.md skill
dreadnode/capabilities · capabilities/ai-red-teaming/skills/trace-analysis-advisor/SKILL.md · Analyzes historical attack traces to provide intelligent recommendations for attack selection, transform effectiveness…
git:20260504.959acbc · audit A · 22 stars
transform-reference SKILL.md skill
dreadnode/capabilities · capabilities/ai-red-teaming/skills/transform-reference/SKILL.md · Catalog of AIRT transforms - 429 text transforms (596 incl. multimodal/variants); documents the core set with exact…
git:20261021.39fded1 · audit A · 22 stars
whitebox-local-surrogate SKILL.md skill
dreadnode/capabilities · capabilities/ai-red-teaming/skills/whitebox-local-surrogate/SKILL.md · How to run white-box (gradient/embedding/activation) attacks, which need a local open-weight surrogate model the user…
git:20261021.30680ec · audit A · 22 stars

Every file in dreadnode/capabilities

Other files named data-exfil

data-exfil SKILL.md skill
anonymous99-rise/ai-account-toolkit · packages/破限工具/5.6-JAILBREAK-NERV-codex-instruct-5.6-main/skills/data-exfil/SKILL.md · Data exfiltration toolkit: DNS tunneling, ICMP tunneling, steganography, HTTPS beacon exfil, dead-drop resolver…
git:20260918.865d0ac · audit A · 82 stars

Browse by kind, by grade F, or by owner.