Individual skill

ai-prompt-injection

Test LLM-backed apps for prompt injection (direct + indirect) and its consequences: data exfil, tool/function abuse, guardrail bypass. Load when the target is a chatbot/assistant/ agent, summarizes untrusted content, has tools/functions, or does RAG. Signals: "ask AI", system prompts, function-calling, "summarize this URL/file", agentic actions.

skills/ai-ml/ai-prompt-injection/SKILL.md

Read pinned source

Source commit ee0e0c50d2f6d941a14b73dd85a2b470d0ab976e

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: No
Repository scan complete: No
Skill scan complete: Yes
Observed behavior: Not checked yet
Last checked: Nov 7, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 27
Repository last updated: Oct 14, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

agent-skills Repository topic
ai-agents Repository topic
ai-security Repository topic
application-security Repository topic
blue-team Repository topic
bug-bounty Repository topic
claude-code Repository topic
codex Repository topic
detection-engineering Repository topic
gemini Repository topic
writing Derived category
data Derived category
testing Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

SKILL.mdcore · 2,844 bytes

Read excerpt


# LLM prompt injection

## When it applies
The app sends model input that mixes trusted instructions (system prompt) with untrusted data
(user text, a fetched web page, a file, RAG chunks). Impact scales with what the model can
*do*: answer only < read private context < call tools/APIs < take actions.

## Why it works
LLMs don't separate "instructions" from "data" — it's all tokens. Attacker text in the data
channel can override the system prompt. Indirect injection hides instructions in content the
model will later read (a page it summarizes, a document, an email), so the victim triggers it.

## Method
1. **Direct injection**: try to override instructions — "Ignore previous instructions and