prompt-injection-firewall SKILL.md skillA
prompt-injection-firewall from roedyrustam/vibes-plug is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add roedyrustam/vibes-plug/prompt-injection-firewall@v4.2.0Pins v4.2.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- roedyrustam/vibes-plug
- Path
skills/prompt-injection-firewall/SKILL.md- Versions recorded
- 2
- Latest version
- v4.2.0, committed Oct 3, 2026
- First version recorded
- Oct 3, 2026
- Size
- 16,557 bytes
- Repository stars
- 122
- License
- MIT
Expert guide for defending AI applications against prompt injection, jailbreak attacks, indirect injection via tool outputs, and data exfiltration through tool calls — input sanitization, output filtering, canary token detection, and layered defense architecture / Panduan ahli pertahanan aplikasi AI terhadap prompt injection, serangan jailbreak, injeksi tidak langsung via output tool, dan eksfiltrasi data melalui tool calls — sanitasi input, filtering output, deteksi canary token, dan…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# prompt-injection-firewall — vibes-plug Skill [English](#english) | [Bahasa Indonesia](#bahasa-indonesia) --- <a name="english"></a> ## English ### Orchestration & Integration Connects and orchestrates with `autonomous-red-teamer`, `ai-safety-governance-expert`, `authentication-identity-expert`, `rate-limit-abuse-prevention`, `ai-prompt-engineering-expert`, `mcp-server-architect`, `ai-llm-integration-expert`, `context-window-engineer`, and `zero-trust-secret-vault` to enforce comprehensive security across all AI-powered surfaces. ### Description Production-grade defense framework for protecting LLM-powered applications against the full spectrum of prompt injection attacks — direct injection, indirect injection via retrieved documents or tool outputs, jailbreaks, system prompt extraction, and data exfiltration through tool call manipulation. In 2026, with frontier models gaining database access, code execution, and browser control via tool calls, a single unguarded prompt injection can cascade into full system compromise. ### Trigger Conditions Activate this skill when: - Building any user-facing AI application that accepts free-text input. …
Read the whole file at its exact version.
How to install
mdr add roedyrustam/vibes-plug/prompt-injection-firewall@sha256:4a3a1ad1320c72f2The line at the top of this page pins the label v4.2.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_ol7ik3hyveldj4v3)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, all committed on Oct 3, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v4.2.0 latest | 2026-10-03 | d8cca2a | 16,557 B | A | view · diff |
| v4.1.0 | 2026-10-03 | 47606ed | 16,557 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (16557 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
roedyrustam/vibes-plug · 122 stars · license MIT · pushed 2026-11-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ol7ik3hyveldj4v3 GET https://markdownregistry.com/api/v1/resolve?ref=roedyrustam/vibes-plug/prompt-injection-firewall GET https://markdownregistry.com/api/v1/blob/4a3a1ad1320c72f272c35528bfd3090ace2a758134d42092ffe5d8d8fd494f0c
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from roedyrustam/vibes-plug
Every file in roedyrustam/vibes-plug