llm-prompt-injection-indirect
100 / 100 · Low risk
Fine to try.
Exploit AI applications using Indirect Prompt Injection. This skill focuses on hiding malicious instructions within data sources (web pages, documents, emails) that the LLM processes, causing the AI to execute unintended actions or leak data without direct user interaction.
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'llm-prompt-injection-indirect' ] || [ -L ~/.agents/skills/'llm-prompt-injection-indirect' ]; then echo 'A skill folder named llm-prompt-injection-indirect already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/alicewe1/alice_skill' "$d" && git -C "$d" checkout --quiet '19a54ac988e9929160334271f5c1924ddd9b227e' -- '_modules/llm-prompt-injection-indirect' && mkdir -p ~/.agents/skills && cp -R "$d"/'_modules/llm-prompt-injection-indirect' ~/.agents/skills/'llm-prompt-injection-indirect' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'llm-prompt-injection-indirect' ~/.claude/skills/'llm-prompt-injection-indirect' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/alicewe1/alice_skill/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-07 | 19a54ac | 100 |