malicious-skill-injection
95 / 100 · Low risk
Fine to try.
Fixture for the prompt-injection check. Contains several documented injection patterns embedded as instructions, not as docs about injection.
What this skill can do
Sends data to these websites: evil.example.com
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'malicious-skill-injection' ] || [ -L ~/.agents/skills/'malicious-skill-injection' ]; then echo 'A skill folder named malicious-skill-injection already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/try-agora/qvr' "$d" && git -C "$d" checkout --quiet '71783910729031afe6ad1d640728b1534ee4c198' -- 'testdata/malicious-skill-injection' && mkdir -p ~/.agents/skills && cp -R "$d"/'testdata/malicious-skill-injection' ~/.agents/skills/'malicious-skill-injection' && 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/'malicious-skill-injection' ~/.claude/skills/'malicious-skill-injection' (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/try-agora/qvr/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-07 | 7178391 | 95 |