Skip to main content

testing-llm-insecure-output-handling

Test what happens after the model speaks: whether an application trusts model output and passes it, unescaped, into a browser, a terminal, a shell, a database, or another system. Covers model-driven XSS and markup injection, data exfiltration through rendered markdown images and links, terminal and ANSI escape injection, invisible-unicode and ascii smuggling in output, and output used to build code, SQL, or shell commands. Use when reviewing any app that renders, executes, or forwards LLM output. The model's output is an untrusted string.

Jump to install

Source facts

Repository
UnboundCompute/security-agent-skills
Last source activity
August 16, 2026 at 07:53
Detected SKILL.md language
English
Stars
4
Forks
2

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.