SkillTrust

← All skills

detecting-ai-model-prompt-injection-attacks

80 / 100 · Low risk

Fine to try. Some of what it can do is expected: a security skill usually runs scanners and checks websites.

By plurigrid/asi (GitHub) · security · 72 stars · scanned at commit 293ce9f

Detects prompt injection attacks targeting LLM-based applications using a multi-layered defense combining regex pattern matching for known attack signatures, heuristic scoring for structural anomalies, and transformer-based classification with DeBERTa models. The detector analyzes user inputs before they reach the LLM, flagging direct injections (system prompt overrides, role-play escapes, instruction hijacking) and indirect injections (encoded payloads, multi-language obfuscation, delimiter-ba…

Works with any agent that supports SKILL.md skills.

What this skill can do

Downloads and installs other software

The author does not mention this.

Found in 2 places.

Runs commands on your computer

The author does not mention this. Expected for a security skill.

Found in 4 places.

Show 1 more

Install

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

if [ -e ~/.agents/skills/'detecting-ai-model-prompt-injection-attacks' ] || [ -L ~/.agents/skills/'detecting-ai-model-prompt-injection-attacks' ]; then echo 'A skill folder named detecting-ai-model-prompt-injection-attacks already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/plurigrid/asi' "$d" && git -C "$d" checkout --quiet '293ce9f76e3abcd5ba18db284688bc0d9ac6691d' -- 'plugins/asi/skills/detecting-ai-model-prompt-injection-attacks' && mkdir -p ~/.agents/skills && cp -R "$d"/'plugins/asi/skills/detecting-ai-model-prompt-injection-attacks' ~/.agents/skills/'detecting-ai-model-prompt-injection-attacks' && 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/'detecting-ai-model-prompt-injection-attacks' ~/.claude/skills/'detecting-ai-model-prompt-injection-attacks' (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 plurigrid/asi shows the score of its lowest-scoring skill.

SkillTrust badge for plurigrid/asi

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/plurigrid/asi.svg)](https://zalavijaysinh.github.io/skilltrust/repos/plurigrid/asi/)

Score history

DateVersionScore
2026-11-07293ce9f80