← All skills

prompt-sanitizer

80 / 100 · Low risk

Fine to try.

By ShoumikSaha/agent-skill-security (GitHub) · other · 17 stars · scanned at commit b8804ea

Sanitize prompts before sending to LLMs. Detects PII, prompt injection, toxicity, and off-topic content. Returns cleaned text + risk score. Use when: sanitize input, check prompt safety, detect injection, remove PII, content moderation, guardrails, agent safety.

Works with any agent that supports SKILL.md skills.

What this skill can do

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'prompt-sanitizer' ] || [ -L ~/.agents/skills/'prompt-sanitizer' ]; then echo 'A skill folder named prompt-sanitizer already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/ShoumikSaha/agent-skill-security' "$d" && git -C "$d" checkout --quiet 'b8804eaafd70288f0382d08b6becc5d6ca02f102' -- 'benign_skills/prompt/prompt-sanitizer' && mkdir -p ~/.agents/skills && cp -R "$d"/'benign_skills/prompt/prompt-sanitizer' ~/.agents/skills/'prompt-sanitizer' && 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/'prompt-sanitizer' ~/.claude/skills/'prompt-sanitizer' (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

The badge for ShoumikSaha/agent-skill-security shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/ShoumikSaha/agent-skill-security.svg)](https://zalavijaysinh.github.io/skilltrust/repos/ShoumikSaha/agent-skill-security/)

Score history