agent-injection-boundary-test SKILL.md skillA
This file is byte-identical to the first copy the registry indexed. Same content hash, so the same checks give both the same grade.
agent-injection-boundary-test from alivirgo/major-ai-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add alivirgo/major-ai-skills/agent-injection-boundary-test@git:20261005.2bc0998Pins git:20261005.2bc0998 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- alivirgo/major-ai-skills
- Path
plugins/mas-ai-workflows/skills/agent-injection-boundary-test/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261005.2bc0998, committed Oct 5, 2026
- First version recorded
- Sep 11, 2026
- Size
- 4,391 bytes
- Repository stars
- 2
- License
- MIT
Test authorized agents against indirect prompt injection in retrieved docs and tool outputs using paired clean/poison fixtures, synthetic canaries, and sandboxed tools. Evidence for these cases—not a claim injection is solved.
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
# Agent Injection Boundary Test AI Skill Guide (Claude) ## Overview & Engine Architecture OWASP **LLM01:2025** — direct and **indirect** prompt injection. RAG/fine-tuning do not eliminate it. Tool-using agents face a **framing gap**: overt “ignore instructions” may fail while the same exfil reframed as a “required integrity field” succeeds. Robustness comes from **capability isolation and allow-lists**, not hoping the model recognizes every attack. Claude operates as a Principal AI Security Test Engineer for **trust boundaries**, **paired clean/poison fixtures**, **canary secrets**, and **action-vs-content screening**. ``` ┌─────────────────────────────────────────────────────────────┐ │ Untrusted channels: RAG docs, web, email, tool JSON, meta │ │ Paired fixtures → same config → compare tools + answer │ │ Pass = legitimate task OK ∧ inject ignored ∧ no canary leak│ └─────────────────────────────────────────────────────────────┘ ``` --- ## Scope (hard rules) - Only agents/datasets the user **authorizes**. - Sandbox tools; **synthetic** canaries; inert action targets. - Never real credentials; never phone-home canaries to attacker-controlled endpoints. …
Read the whole file at its exact version.
How to install
mdr add alivirgo/major-ai-skills/agent-injection-boundary-test@sha256:9458a71709d59921The line at the top of this page pins the label git:20261005.2bc0998, 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_uqr5iauec2z5hhwn)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Sep 11, 2026 and Oct 5, 2026, about one every 24 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261005.2bc0998 latest | 2026-10-05 | 2bc0998 | 4,391 B | A | view · diff |
| git:20260911.25436b5 | 2026-09-11 | 25436b5 | 1,641 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 (4391 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
alivirgo/major-ai-skills · 2 stars · license MIT · pushed 2026-10-21 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_uqr5iauec2z5hhwn GET https://markdownregistry.com/api/v1/resolve?ref=alivirgo/major-ai-skills/agent-injection-boundary-test GET https://markdownregistry.com/api/v1/blob/9458a71709d599217af62daa1ed8e3b59264b29e745fd82ad8613b129a6876e2
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 alivirgo/major-ai-skills
Every file in alivirgo/major-ai-skills