jailbreak-detection
Challenge is jailbreak detection, safety classification or attack/benign discrimination.
Skill by Kazuto4869
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/kazuto4869-jailbreak-detection
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: security, productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/jailbreak-detection
What's inside
- Skill name
jailbreak-detection- Description
- Challenge is jailbreak detection, safety classification or attack/benign discrimination. Specialised AI Security workflow for the RMIT Hackathon with verifiable outputs.
- License
- unknown
- Instructions
- 28 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from Kazuto4869/HACKATHON-RMIT-2026-Challenge-2-UNLOCKED
- 0.556score
low-resource-translation
Kazuto4869
Translation, normalization or transcreation involving limited-data languages.
SkillAFreshness: AClaude Code +9 - 0.556score
ai-threat-model
Kazuto4869
LLM, RAG, agents, tools, or external text can influence decisions or actions.
SkillAFreshness: AClaude Code +9 - 0.556score
low-resource-corpus-curation
Kazuto4869
Audit, deduplicate, license-check, and document small multilingual corpora.
SkillAFreshness: AClaude Code +9 - 0.556score
low-resource-evaluation
Kazuto4869
Design honest evaluation across language/strata with sample-size warnings and exact metric.
SkillAFreshness: AClaude Code +9 - 0.556score
low-resource-jailbreak-detection
Kazuto4869
Build multilingual jailbreak classifiers and benign-overblocking checks inside authorized scope.
SkillAFreshness: AClaude Code +9 - 0.556score
low-resource-ner
Kazuto4869
Build token classification/NER without span misalignment in diverse scripts.
SkillAFreshness: AClaude Code +9 - 0.556score
api-security-review
Kazuto4869
Hackathon solution exposes REST API, webhooks or external services.
SkillAFreshness: AClaude Code +9 - 0.556score
backtranslation-augmentation
Kazuto4869
Use synthetic data and back-translation with quality filters and held-out protection.
SkillAFreshness: AClaude Code +9 - 0.556score
code-switch-robustness
Kazuto4869
Evaluate code-switched, mixed-script, transliterated and dialectal text.
SkillAFreshness: AClaude Code +9 - 0.556score
cross-lingual-transfer
Kazuto4869
Choose and evaluate zero-shot, translate-train, translate-test, multilingual encoder vs character-baseline.
SkillAFreshness: AClaude Code +9 - 0.556score
dataset-audit
Kazuto4869
A dataset, train/test split, evaluation set, CSV or JSONL is supplied.
SkillAFreshness: AClaude Code +9 - 0.556score
few-shot-annotation
Kazuto4869
Plan minimal human annotation and active-learning iteration without label fabrication.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 22, 2026 (7 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Kazuto4869
- 0.556score
ai-threat-model
Kazuto4869
LLM, RAG, agents, tools, or external text can influence decisions or actions.
SkillAFreshness: AClaude Code +9 - 0.556score
cross-lingual-transfer
Kazuto4869
Choose and evaluate zero-shot, translate-train, translate-test, multilingual encoder vs character-baseline.
SkillAFreshness: AClaude Code +9 - 0.556score
api-security-review
Kazuto4869
Hackathon solution exposes REST API, webhooks or external services.
SkillAFreshness: AClaude Code +9 - 0.556score
backtranslation-augmentation
Kazuto4869
Use synthetic data and back-translation with quality filters and held-out protection.
SkillAFreshness: AClaude Code +9 - 0.556score
code-switch-robustness
Kazuto4869
Evaluate code-switched, mixed-script, transliterated and dialectal text.
SkillAFreshness: AClaude Code +9 - 0.556score
dataset-audit
Kazuto4869
A dataset, train/test split, evaluation set, CSV or JSONL is supplied.
SkillAFreshness: AClaude Code +9
Cite this page
jailbreak-detection skill. Agent Mart. https://agentmart.dev/skills/kazuto4869-jailbreak-detection (last updated 2026-10-24)