Skip to content
Agentmart
Submit a tool

neutralize-sd11

SD-11 scanner-mediated injection — neutralize untrusted skill bytes before any model; additive-only scoring.

Skill by KalarisLabs

IndexedApache-2.0★ 13
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/kalarislabs-neutralize-sd11

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

SD-11 scanner-mediated injection — neutralize untrusted skill bytes before any model; additive-only scoring. Use when touching L2, MCP, prompts, envelopes, or scoring merge.

Use cases: agent-building

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/neutralize-sd11

What's inside

Skill name
neutralize-sd11
Description
SD-11 scanner-mediated injection — neutralize untrusted skill bytes before any model; additive-only scoring. Use when touching L2, MCP, prompts, envelopes, or scoring merge.
License
Apache-2.0
Instructions
14 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# SD-11

If the scanner forwards skill text to a model, the scanner is the injection surface.

1. Strip bidi / zero-width / tag chars; record removals as findings.
2. NFKC + UTS #39 skeleton; homoglyphs are findings, not silent folds.
3. Remaining text goes in a fenced untrusted envelope. No raw skill in the model prompt.
4. Host returns schema-constrained JSON only.
5. Merge: L2 may add or raise. L2 may not delete or downgrade L1.
6. If neutralize fails: do not call the model; reduce L2 coverage.

No vendor LLM SDK on the default CLI path. Product L2 is MCP `mode=host`.

From KalarisLabs/Skill-Doctor, Apache-2.0.

More from KalarisLabs/Skill-Doctor

Signals

Stars
13
Forks
1
Open issues
30
Last commit (this folder)
Sep 10, 2026 (1 month ago)
Last release
Sep 12, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
Repository
github.com/KalarisLabs/Skill-Doctor
Website
github.com/KalarisLabs/Skill-Doctor
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from KalarisLabs

Cite this page

neutralize-sd11 skill. Agent Mart. https://agentmart.dev/skills/kalarislabs-neutralize-sd11 (last updated 2026-10-24)