SkillPedia Skills Encyclopedia
中文 EN
Today's updates 2026-11-18 UTC

No new commits yet today

Open the update feed

tirithsheeki03/tirith

Performs a security check on terminal commands and external references before execution, blocking homograph domains,…

No ratings yet Rate this skill
Stars2.8k
Forks97
Watchers2.8k
Open Issues25

InstallOne-line install

Installable · 4 skills

This repository follows the Agent Skills spec, so one command installs it into your AI client — works across Claude Code, Codex, Cursor, Copilot, Windsurf, and 18+ other clients.

npx skills@latest add sheeki03/tirith

4 more are not listed — run npx skills@latest add sheeki03/tirith --list to see them all.

Add -g install globally (available in every project) · add --agent claude-code to target a client · add --yes to skip the prompts. Restart your AI client afterward and it will pick it up.

OverviewOverview

Key Features

Performs a security check on terminal commands and external references before execution, blocking homograph domains, suspicious URLs and malicious Docker image references to reduce supply chain poisoning risk. Key capabilities include: 1. Tiered detection pipeline: Tier 1 uses compiled regex for a sub-millisecond fast gate, Tier 2 extracts URL and Docker references and performs byte-level scanning, Tier 3 conducts deep analysis of suspicious targets, escalating gradually to avoid false positives and performance loss; 2. Unicode homograph attack detection: compares code points against visually similar glyphs to identify phishing links that disguise themselves as legitimate domains using Cyrillic letters and similar tricks; 3. URL and image reference validation: parses URLs, Docker image tags and repository addresses in commands, flagging references to unknown or high-risk sources; 4. AI tool protection integration: provides setup steps to wire this check into the command execution path of AI coding tools, so Agent-generated commands pass a security gate before running.

Use Cases

Before developers paste and run install scripts of unknown origin in the terminal, before CI pipelines pull third-party images, when AI coding assistants auto-generate and execute shell commands, and when investigating suspected phishing domains or typosquatted package names.

Target Roles

Network and System Security Engineer, DevOps / Operations Engineer, Backend Developer, AI / Algorithm Engineer.

TopicsTopics

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID353
Data sourceGitHub
Repositorysheeki03/tirith
CategoryAI & Agent Skills / Security & Compliance Tools
Primary languageRust
LicenseGNU Affero General Public License v3.0
Default branchmain
GitHub repository ID1147679251
Node IDR_kgDORGgyEw
Rank#353 (position within the source ranking)
Site-wide popularity rank#422 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

01k2k3k2026-09-292026-10-112026-09-29 · 2,7472026-10-11 · 2,751
  • Now2,751
  • Previous point · 09-29 2,747
  • vs previous point +4
  • 2 data points 12 days
02550751002026-09-292026-10-112026-09-29 · 972026-10-11 · 97
  • Now97
  • Previous point · 09-29 97
  • vs previous point ±0
  • 2 data points 12 days

TimelineTimeline

Repository created2026-02-02 04:33:479 months ago
Data last updated2026-10-26 11:56:5023 days ago
Last commit2026-10-10 04:36:141 months ago

CommitLatest commit

Committed by github-actions. Update Category: Dependency Upgrades & Maintenance. Commit details: chore: update threatdb manifest to v1791693415133. This update refreshes dependencies and build configuration.

1abd774 github-actions 2026-10-11

Next stepsNext steps