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

No new commits yet today

Open the update feed

Claude-RedSnailSploit/Claude-Red

A red team skill pack for Claude-based AI agents that turns security offense/defense procedures into skills the agent ca…

No ratings yet Rate this skill
Stars8.8k
Forks1.1k
Watchers8.8k
Open Issues32

InstallOne-line install

Unconfirmed

Whether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:

git clone https://github.com/SnailSploit/Claude-Red.git

OverviewOverview

Key Features

A red team skill pack for Claude-based AI agents that turns security offense/defense procedures into skills the agent can invoke directly, making model security assessment a reusable standard action instead of manual probing. Key capabilities include: 1. Red team skill injection: mounts red team test instruction sets as Claude Skills so the agent can call them during security assessment tasks without rewriting attack prompts each time; 2. Attack technique coverage: ships templates for common adversarial methods such as prompt injection, jailbreak bypass, and role-play manipulation to probe the guardrail boundaries of target models and agents; 3. Test workflow orchestration: chains reconnaissance, payload construction, trial execution, and result logging into repeatable steps for multi-round regression comparison of defense effectiveness.

Use Cases

pre-launch security baseline checks for AI agents, bypass validation of prompt guardrail policies, batch generation of adversarial samples during red team exercises, and defense regression testing after model version updates.

Target Roles

Network & System Security Engineer, AI / Algorithm Engineer, Test / QA 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 ID244
Data sourceGitHub
RepositorySnailSploit/Claude-Red
CategoryAI & Agent Skills / Security Testing & Red Team Skills
Primary languagePython
LicenseMIT License
Default branchmain
GitHub repository ID1172273835
Node IDR_kgDORd96qw
Rank#134 (position within the source ranking)
Site-wide popularity rank#164 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

02.5k5k7.5k10k2026-09-262026-10-242026-09-26 · 6,9322026-10-16 · 7,5442026-10-23 · 7,9132026-10-24 · 8,760
  • Now8,760
  • Previous day · 10-23 7,913
  • vs previous day +847
  • 4 data points 28 days
05001k1.5k2026-09-262026-10-242026-09-26 · 9072026-10-16 · 9832026-10-23 · 1,0562026-10-24 · 1,123
  • Now1,123
  • Previous day · 10-23 1,056
  • vs previous day +67
  • 4 data points 28 days

TimelineTimeline

Repository created2026-03-04 05:52:358 months ago
Data last updated2026-10-26 11:53:4023 days ago
Last commit2026-10-12 15:02:401 months ago

CommitLatest commit

Committed by SnailSploit. Update Category: Documentation Updates. Commit details: Update README.md. This update refines the documentation for easier onboarding.

739512a SnailSploit 2026-09-19