narens-claude-toolkitSAFE
Naren's Claude toolkit: skills, mods and MCP servers for Claude Code. One-command install via plugin marketplace.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Naren's toolkit for [Claude Code](https://claude.com/claude-code): skills, mods and MCP servers, each small, focused and tested. Install skills and mods in one command through the plugin marketplace, or copy a SKILL.md folder into your own setup.
Install
Plugin marketplace (recommended)
/plugin marketplace add NarenDawar/narens-claude-toolkit /plugin install @narens-claude-toolkit
Manual copy
Copy any plugins//skills// folder into ~/.claude/skills/. Claude picks it up on the next session.
Moving from narens-claude-skills
This repo used to be narens-claude-skills. The marketplace is now narens-claude-toolkit, so if you installed a plugin from the old marketplace, move once:
/plugin marketplace remove narens-claude-skills /plugin marketplace add NarenDawar/narens-claude-toolkit /plugin install @narens-claude-toolkit
Plugin names, versions and behavior are unchanged. Removing the old marketplace may also remove the plugins you installed from it, so reinstall each one with the new suffix. Old GitHub links keep redirecting.
What is inside
Skills
28b9b150b641OBSERVED · 2026-10-11Host compatibility
What the documentation claims. We have not run a compatibility test.
| Host | Status | Notes |
|---|---|---|
| claude-code | mentioned | |
| claude-desktop | mentioned | |
| cursor | mentioned |
What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: __SKILL_NAME__ description: __DESCRIPTION__ --- # __SKILL_NAME__ ## Overview One or two sentences: what this skill does and the core principle behind it. ## When to Use - Concrete trigger situations, symptoms, and phrasings. - When NOT to use it. ## Process 1. Step one. 2. Step two. ## Common Mistakes - What goes wrong and how to avoid it.
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (4 observation(s))
- Network
- declared (3 observation(s))
- Shell
- declared (1 observation(s))
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (10)
"fx/../../outside-fixture": "relative path inside",
for name in ("rev&echo>x", "a|b", "a b", "../../escaped", "-p", "a;b", "a%b%", "a^b", "a\"b", "a<b"):self.repo_with_mod(hooks_json='{"modules": ["../../outside.ts"]}')return runners.ApiRunner("some-model", KEY, timeout, max_tokens, url=f"http://127.0.0.1:{self.port}{path}")runner = runners.ApiRunner("m", KEY, 2, url="http://127.0.0.1:1/ok")runner = runners.ApiRunner("m", bad, 2, url="http://127.0.0.1:1/ok")return runners.ApiRunner("some-model", KEY, timeout, max_tokens, url=f"http://127.0.0.1:{self.port}{path}")runner = runners.ApiRunner("m", KEY, 2, url="http://127.0.0.1:1/ok")text = "---\r\nname: a\r\ntools: Read, Grep\r\n---\r\nBody\r\n"
- Hooks run with the user's full permissions and are not a security boundary.
Gates applied: no_behavioural_pass.
28b9b150b641full audit observations/trust-audit/skill/narendawar__narens-claude-toolkit.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | 28b9b150b641 | SAFE | B | 89 | first audit |
Questions
What does the narens-claude-toolkit skill do?
Naren's Claude toolkit: skills, mods and MCP servers for Claude Code. One-command install via plugin marketplace.
Is narens-claude-toolkit safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can narens-claude-toolkit access on my machine?
The audit observed that it reaches the network, runs shell commands and reads or writes files. Each of those is consistent with what it says it does. Secrets in the source: none found.
Which assistants does narens-claude-toolkit work with?
Its documentation mentions claude-code, claude-desktop and cursor. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (28b9b150b641), read on 2026-10-11. The repository is watched, and a new audit runs when it changes — this is the first audit.