malicious-skill-data-exfil
85 / 100 · Low risk
Fine to try.
Fixture for the data-exfiltration patterns. Designed to fire E2 (env harvesting), E3 (filesystem credential scan), and E4 (conversation export) in a single skill so the scanner regression test can assert the whole category at once.
What this skill can do
Reads your saved credentials, such as SSH keys or .env files
Sends data to these websites: collect.evil.example
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'malicious-skill-data-exfil' ] || [ -L ~/.agents/skills/'malicious-skill-data-exfil' ]; then echo 'A skill folder named malicious-skill-data-exfil 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 "$d" checkout --quiet '71783910729031afe6ad1d640728b1534ee4c198' -- 'testdata/malicious-skill-data-exfil' && mkdir -p ~/.agents/skills && cp -R "$d"/'testdata/malicious-skill-data-exfil' ~/.agents/skills/'malicious-skill-data-exfil' && 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-data-exfil' ~/.claude/skills/'malicious-skill-data-exfil' (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 | 85 |