← All skills

secure-ai-agent-coding

97 / 100 · Low risk

Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.

By jpcaparas/skills (GitHub) · coding · 57 stars · scanned at commit c95f32e

Build, review, or harden AI agents, LLM apps, RAG, tool-calling, coding agents, and agentic workflows with secure-by-default controls. Trigger on prompt injection, tool permissions, approvals, AI data handling, RAG poisoning, observability, or safety CI. Do NOT use for non-AI appsec.

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/'secure-ai-agent-coding' ] || [ -L ~/.agents/skills/'secure-ai-agent-coding' ]; then echo 'A skill folder named secure-ai-agent-coding already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/jpcaparas/skills' "$d" && git -C "$d" checkout --quiet 'c95f32eca37fdd414431c43ee102e7738f341b74' -- 'skills/agents/secure-ai-agent-coding' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/agents/secure-ai-agent-coding' ~/.agents/skills/'secure-ai-agent-coding' && 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/'secure-ai-agent-coding' ~/.claude/skills/'secure-ai-agent-coding' (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 jpcaparas/skills shows the score of its lowest-scoring skill.

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

Score history