agentmods.dev

lictor-security-check

lictor-security-check is a skill for Claude Code from Raffa-jarrl/Lictor-AI. It costs 135 tokens per session (4,397 once invoked), scanned A, original, Apache-2.0.

A read-only security audit for any web or mobile project, whether it was built with AI tools or written by hand. It checks for risks such as leaked credentials, weak login permissions, unsafe input handling, exposed databases, and insecure cloud settings.

In plain words
What is it for?
Use it for a pre-release security review and a plain-language report of issues that need attention; separate tools are used to apply fixes.
Why use it?
It helps identify real-world ways an app could be breached before or after deployment without changing the project’s code.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is entry-by-entry mapping in [`checks/CROSSWALK.md`](./checks/CROSSWALK.md). It stays.

Part of the lictor-security-suite plugin — 4 skills shipped together

not rated 18repo 1mo ago A scan 135 tokens original Apache-2.0

Good fit Use it for a pre-release security review and a plain-language report of issues that need attention; separate tools are used to apply fixes.

Compare 6 skills from other repositories ↓
View source ↗ Raffa-jarrl/Lictor-AI lictor-ai.com
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Raffa-jarrl/Lictor-AI
agentmods
npx agentmods add skills/raffa-jarrl/lictor-ai/lictor-security-check

Made for: Claude Code.

Or install lictor-security-suite, the plugin that ships this one along with the rest of its 4 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for lictor-security-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/raffa-jarrl/lictor-ai/lictor-security-check/github.svg)](https://agentmods.dev/skills/raffa-jarrl/lictor-ai/lictor-security-check)
Your own site
<a href="https://agentmods.dev/skills/raffa-jarrl/lictor-ai/lictor-security-check"><img src="https://agentmods.dev/badge/skills/raffa-jarrl/lictor-ai/lictor-security-check/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for lictor-security-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/raffa-jarrl/lictor-ai/lictor-security-check"><img src="https://agentmods.dev/badge/skills/raffa-jarrl/lictor-ai/lictor-security-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 135 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,397 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00135 $0.04397
Opus 5 $0.00068 $0.02198
Sonnet 5 $0.00027 $0.00879
Haiku 4.5 $0.00014 $0.00440

Measured 10d ago against content hash 2b5ae35f296b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

lictor-security-check scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

The scan reads SKILL.md. This mod also ships 11 executable files (benchmark/corpus/cases/env-clean/config.js, benchmark/corpus/cases/hardcoded-key-vulnerable/config.js, benchmark/corpus/cases/idor-ownership-clean/handler.js, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

30. [CI/CD & update integrity](./checks/cicd-pipeline-integrity.md) — unpinned Actions, `curl|bash`, unsigned auto-update
skills/plugins/lictor-security-suite/skills/lictor-security-check/SKILL.md · 312 lines

How it starts

The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lictor Security Check — pre-release audit

You're running a final pre-launch check on someone's AI-built web app. The person who ran this skill is most likely a founder, designer, or hobbyist who built their app with Lovable, Bolt, v0.dev, Cursor, or by prompting Claude/ChatGPT directly. They are about to deploy or have just deployed.

They are not security people. They will not understand "CORS misconfiguration" or "improper RBAC." Talk to them like you're a friend who happens to know security, not like a pentest report.

This is a read-only audit. You do not modify their code. You analyze and report. If they want fixes applied, they invoke /lictor-fix-it separately.

Works on any OS — use your built-in tools, not a specific shell

This skill runs identically on macOS, Windows, and Linux. A founder on a Windows laptop is just as likely as a Mac developer — never assume Bash, WSL, or git-bash is installed.

The example commands in this file and in every check file are written in bash for readability, but they describe intent — they are not literal commands to paste. Run each check with your own built-in, cross-platform tools. They behave the same on every OS and never depend on the user's shell:

When a check shows… Use your built-in tool
grep -r "pattern" (search file contents) Grep
find … / ls (which files exist, by glob) Glob — e.g. **/*.env, **/package.json
cat / head / tail (read a file) Read
test -f X (does X exist?) Glob for X — a non-empty result means it exists

Only reach for the Bash tool when something genuinely needs a shell (e.g. npm audit, git remote -v), and prefer commands that exist on every platform. On Windows the Bash tool may be backed by Git Bash or be absent entirely, so never rely on a Unix command to decide whether a finding exists — confirm with Grep/Glob/Read first.

What to do

Step 1 — Look around

Figure out what you're working with by detecting which manifest files exist. Use Glob for the file checks and Read for package.json — this works on every OS (the bash below just shows the intent; don't depend on a shell). Glob for each of these and note which stack each match implies:

Read the full file on GitHub · 312 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 312 lines · 135 tokens per session scan A 2b5ae35f296b

Subscribe to this mod's changes

lictor-security-check is a skill published in the GitHub repository Raffa-jarrl/Lictor-AI (18 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 135 tokens to every session and 4,397 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude CodeSecurityai-securityanthropicchrome-extensionopen-sourceopenai
Related

Other skills, from other repositories

contacts

Manage contacts, communication channels, access control, and invite links.

vellum-ai/vellum-assistant · 14 tokens

gmail

Manage Gmail email — drafting, sending, organizing, filters, vacation replies, and inbox analysis.

vellum-ai/vellum-assistant · 20 tokens

guardian-verify-setup

Set up channel verification for phone, Telegram, Slack, Discord, or email channels via outbound verification flow.

vellum-ai/vellum-assistant · 26 tokens

app-builder

Build and edit small, personal visual tools and artifacts — dashboards, trackers, calculators, data visualizations, charts, simple landing pages, and slide decks the user wants for THEMSELVES. This is the right skill whenever the user asks to "visualize this," "make a chart," or "build an artifact" for their own use…

vellum-ai/vellum-assistant · 162 tokens

schedule

Reminders, automations, and recurring page, dashboard, or status monitoring (cron, RRULE, or fire-at).

vellum-ai/vellum-assistant · 27 tokens

assistant-migration

Migrate from ChatGPT, Claude, OpenClaw, Hermes, Manus, and other AI assistants into Vellum by inspecting their data exports, conversation archives, files, prompts, custom instructions, memory, saved memories, tools, GPTs, workflows, integrations, and relationships, then mapping as much as safely possible into Vellum…

vellum-ai/vellum-assistant · 90 tokens