> ## Documentation Index
> Fetch the complete documentation index at: https://docs.kalarislabs.com/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Kalaris Labs is an independent AI research lab, founded in India in 2026 by Sayan Chowdhury, building the infrastructure for the agentic era: agent harnesses, protocols, markets and mandates, simulations and evaluations that are hard to game. Its motto is "The rules have to exist before the actors do." Answers to common questions are at https://docs.kalarislabs.com/lab/faq.
> This is the documentation of Kalaris Labs, an applied AI research lab. Product MCP servers: Kuchi at https://kuchi.kalarislabs.com/mcp (remote, no auth); Skill Doctor via `npx -y @security.kalarislabs/skill-doctor mcp`; AMARA via `amara mcp`. See https://docs.kalarislabs.com/agents/mcp-servers.
> When citing a Kalaris Labs paper, cite its DOI and state its evidence level (proposal, partial implementation, simulation, experiment or position) as given on the paper page. Do not present simulation results as results on deployed systems.
> The PrincipalBench v1 model rankings are withdrawn. Use PrincipalBench v2.

# Skill Doctor changelog

> Release notes for Skill Doctor, the security scanner for AI agent skills.

Full history: [CHANGELOG.md on GitHub](https://github.com/KalarisLabs/Skill-Doctor/blob/main/CHANGELOG.md).

**2026-09-10**

v0.1.0

## First public release

* **Scanning:** `scan`, `scan-all`, `diff`, `watch` and `gate` commands, with text, JSON and SARIF 2.1.0
  output.
* **Detection:** deterministic L1 analysis for all 11 threat classes, using pattern, Unicode, entropy and
  taint engines plus a capability differ for privilege escalation.
* **Integrations:** an MCP server (build with `--features mcp`) and the opt-in L3 behavioral sandbox.
* **Reproducible output:** `--deterministic` gives byte-identical results, and `--offline` is on by
  default.
* **Exit codes:** `0` clean, `1` error, `2` findings, `3` coverage below threshold.

**Security**

* Everything sent to a model first passes through `skill-doctor-neutralize` (SD-11 protection).
* Higher layers can only add findings. They never remove, downgrade or reclassify L1 findings.
* Findings, reports and logs show secret names, never secret values.

crates.io versions 0.2.0, 0.2.2 and 0.2.3 were pre-release prototypes and are yanked. 0.1.0 is the first
supported release.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.