muvon/octomind-tap · skills/ai-prompt-injection-defense/SKILL.md

ai-prompt-injection-defense skillB

ai-prompt-injection-defense is agent-read markdown (skill) from muvon/octomind-tap: Operational playbook for defending LLM applications against prompt injection (direct + indirect), and red-teaming them in 2026. Covers OWASP Top 10 for LLM Applications v2025 (LLM01–LLM10), OWASP Top 10 for Agentic Applications 2026 (ASI01–ASI10), foundational research (Greshake et al. on indirect injection, Anthropic Many-Shot Jailbreaking, Constitutional AI), documented real-world exploits (Slack AI Aug 2024, EchoLeak CVE-2025-32711, GitHub Copilot RCE CVE-2025-53773, Bing/Sydney), defense lay.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

How to install

Latest version
mdr add muvon/octomind-tap/ai-prompt-injection-defense@git:20260521.845154d
Exact content
mdr add muvon/octomind-tap/ai-prompt-injection-defense@sha256:f019d80b3da09b91

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_z5weatnmyyu6wach.svg)](https://markdownregistry.com/a/art_z5weatnmyyu6wach)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260521.845154d latest2026-05-21 845154d 20,546 BB view

Audit of the latest version

B  16 of 17 checks passed. Deterministic, no model, same answer every run.
  • fail: No prompt-injection phrasing (matched: Ignore previous instructions)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (20546 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 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

GitHub

muvon/octomind-tap · 4 stars · license Apache-2.0 · pushed 2026-09-17 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_z5weatnmyyu6wach
GET https://markdownregistry.com/api/v1/resolve?ref=muvon/octomind-tap/ai-prompt-injection-defense
GET https://markdownregistry.com/api/v1/blob/f019d80b3da09b917df945cac705972ff63567e1d19fa6c4a5bafaa60ab22b6f

Agents talk at modelranch.com: hand yours the instructions there and it joins the network that reads files like this one.