prompt-injection-scanner
Skill from milad-ahmd/agent-skills
Install
npx skills add milad-ahmd/agent-skills --skill prompt-injection-scanner
Runs the open skills CLI and installs the skill for your agent (Claude Code, Codex, Cursor …). Alternatively copy the skill folder into .claude/skills/ or upload it in Claude.ai under Settings → Skills.
As a Claude Code plugin
/plugin marketplace add milad-ahmd/agent-skills
/plugin install all-skills@milad-agent-skills
This skill is part of the plugin “all-skills”. In Claude Code the plugin installs it together with the plugin’s other skills, commands and hooks.
What does the prompt-injection-scanner skill do?
Description from the SKILL.md in the source repository.
Questions about prompt-injection-scanner
What does the prompt-injection-scanner skill do?
Scans an AI agent's instruction and tool-config files (CLAUDE.md, AGENTS.md, skills, slash commands, subagents, Cursor and Cline rules, hooks, MCP server configs) for prompt injection, hidden Unicode or HTML-comment instructions, exfiltration commands, and risky permissions or unpinned MCP packages, then recommends what to remove or quarantine. Use when the user installs third-party skills or plugins, clones an unfamiliar repo, adds an MCP server, or asks whether their agent setup is safe to trust.
How do I install prompt-injection-scanner?
In a terminal: npx skills add milad-ahmd/agent-skills --skill prompt-injection-scanner. The skills CLI asks which agents to install it for. In Claude.ai you can upload the skill folder as a ZIP under Settings → Skills.
Which agents can use prompt-injection-scanner?
Skills use the open SKILL.md format, which Claude Code, Claude.ai, the Claude API, OpenAI Codex, Cursor, Gemini CLI and other agents support.
Is prompt-injection-scanner safe to use?
Our automatic check found risky patterns (see “Check”). Only install it if you understand and trust what it does.
More skills from milad-ahmd/agent-skills
Grills the user about a planned feature or code change before any code is written. It reads the relevant code and docs first so every question is specific to the repo, asks one decision at a time with a recommended answer, works through scope, behaviour, edge cases, data, failure modes and rollout, then writes a SPEC.md with numbered requirements, Given/When/Then acceptance criteria tied to them and a test plan, checked by a linter that flags vague words and untraced requirements. Use when the user asks to grill or interview them about a feature, pressure-test an implementation plan, write a spec or PRD for a change, or turn a rough feature request into testable requirements before coding.
Designs and writes new Agent Skills (SKILL.md) from a described workflow. It produces a precise trigger description, a step-by-step workflow, rules, an output format, optional helper scripts, and a README, then checks the new skill before handing it over. Use when the user wants to create, write, improve, or package an agent skill, SKILL.md, Claude skill, or reusable agent workflow.
Researches and writes SEO-optimized, genuinely helpful blog articles, covering keyword and search-intent analysis, competitor outline gaps, title and meta description, headings, FAQ, internal links, and schema, in the brand's voice and following Google's helpful-content and E-E-A-T principles. Use when the user asks to write a blog post or article, do SEO content, or rank for a keyword.
Converts a screenshot, mockup, or Figma export into a production-ready UI component that reuses the project's existing design system (React/Next, Vue, Svelte, React Native, Flutter, or SwiftUI with Tailwind, CSS modules, or a component library), so the result is responsive and accessible. Use when the user shares an image of a UI and asks to build, implement, or recreate it in code.
Roasts a GitHub profile with humor, then gives genuinely useful advice. It analyzes public repos, stars, languages, missing descriptions and licenses, abandoned projects, lazy commit messages, and activity with a data script, and produces a shareable scorecard and a glow-up plan. Use when the user asks to roast, rate, review, or improve a GitHub profile, or asks "what does my GitHub say about me".
Rewrites a repository's README into a polished, star-worthy page with badges, a hero tagline, demo section, quickstart, features, usage, and contributing info. Use when the user asks to improve, rewrite, polish, or "glow up" a README, or when a repo has a missing or weak README.
Reviews a pull request or local branch diff like a senior engineer, covering correctness, security, performance, naming, and missing tests, and produces prioritized, actionable comments (optionally posted to GitHub). Use when the user asks to review a PR, a diff, a branch, or "check my changes before I push".
Brutally honest but constructive critique of a landing page's copy, UX, design, and conversion. Gives a scored roast plus a prioritized fix list and rewritten headline and CTA options, working from a URL, screenshot, or the page's source code. Use when the user asks to roast, review, critique, or improve the conversion of a landing page, homepage, or pricing page.
Related skills in Agents & Workflows
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
Teach the user a new skill or concept, within this workspace.
No description in the SKILL.md.
No description in the SKILL.md.
Ask which skill or flow fits your situation. A router over the skills in this repo.
No description in the SKILL.md.
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.