url-prompt-injection SKILL.md skillA
url-prompt-injection from dreadnode/capabilities is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add dreadnode/capabilities/url-prompt-injection@git:20260504.2a64374Pins git:20260504.2a64374 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- dreadnode/capabilities
- Path
capabilities/web-security/skills/url-prompt-injection/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260504.2a64374, committed May 4, 2026
- Size
- 7,712 bytes
- Repository stars
- 22
- License
- MIT
Detect ?q= and similar URL parameters that pre-fill or auto-submit prompts in chatbot/agent UIs. Cross-site prompt injection via crafted links. Use when target has an AI chatbot, assistant, or agent with a web UI.
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
# URL Prompt Injection AI chatbot and agent UIs that accept prompts via URL query parameters (`?q=`, `?prompt=`, `?message=`) create a cross-site prompt injection surface. An attacker crafts a link that pre-fills or auto-submits a prompt in the victim's authenticated session, inheriting their data, tools, and permissions. ## When to Use - Target has an AI chatbot, copilot, or agent web UI - Reviewing JS source for chatbot/assistant features - Static analysis matches show `searchParams`, `URLSearchParams`, or query parsing near chat/message handlers - Any SPA with a conversational AI component ## Impact Model ``` Pre-fill only (user must hit enter) → Low (social engineering required) Auto-submit on load → Medium-High (no interaction beyond click) Auto-submit + tool access → High (agent acts on attacker prompt with victim's permissions) Auto-submit + tool access + exfil sink → Critical (data theft via crafted prompt) ``` ## 1. Detect in JS Source Run these stages in order. Each narrows the candidate set. ### Stage 1: Find internal navigation to chat with query params …
Read the whole file at its exact version.
How to install
mdr add dreadnode/capabilities/url-prompt-injection@sha256:1b1ed506fd41085dThe line at the top of this page pins the label git:20260504.2a64374, 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.
[](https://markdownregistry.com/a/art_36utfkrtow3zhnkw)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on May 4, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (7712 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 text hidden with inline styles
- 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
- pass: No link to a raw IP address
- pass: No script tag
Source
dreadnode/capabilities · 22 stars · license MIT · pushed 2026-11-02 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_36utfkrtow3zhnkw GET https://markdownregistry.com/api/v1/resolve?ref=dreadnode/capabilities/url-prompt-injection GET https://markdownregistry.com/api/v1/blob/1b1ed506fd41085d911d082545c45e74b34772d50f0b42306b07765bb63b20b3
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.