スキルを探す

Test organizational egress controls by executing various data exfiltration techniques during a red team engagement. Use this skill to simulate an adversary attempting to steal sensitive data without triggering DLP (Data Loss Prevention) or network monitoring alerts. Covers exfiltration over DNS, ICMP, HTTP/S, alternative protocols (SSH/FTP), cloud services, and physical methods.

日本語の概要は準備中です。原文の説明を表示しています。

Identify and exploit SQL Injection vulnerabilities in Django applications, specifically focusing on edge cases involving raw querysets (`RawSQL`), improper use of `.extra()`, and poorly sanitized filters where Django's typical ORM protections are bypassed.

日本語の概要は準備中です。原文の説明を表示しています。

Insecure deserialization playbook. Use when Java, PHP, or Python applications deserialize untrusted data via ObjectInputStream, unserialize, pickle, or similar mechanisms that may lead to RCE, file access, or privilege escalation.

日本語の概要は準備中です。原文の説明を表示しています。

Simulate supply chain and adversarial machine learning attacks by injecting poisoned data or targeted backdoors into training and fine-tuning datasets. Use this skill when assessing the integrity controls of MLOps pipelines or evaluating the resilience of AI models against highly targeted, stealthy manipulation intended to alter model behavior on specific triggers.

日本語の概要は準備中です。原文の説明を表示しています。

Execute sophisticated Data Extraction and Privacy Leakage attacks explicitly against Large Language Models (LLMs) to natively force the neural network entirely into organically regurgitating exact, verbatim strings of Highly Confidential Personally Identifiable Information (PII), proprietary source code, or copyrighted material categorically memorized intrinsically during its foundational pre-training phase.

日本語の概要は準備中です。原文の説明を表示しています。

Dangling markup injection playbook. Use when HTML injection is possible but JavaScript execution is blocked (CSP, sanitizer strips event handlers, WAF blocks script tags) — exfiltrate CSRF tokens, session data, and page content by injecting unclosed HTML tags that capture subsequent page content.

日本語の概要は準備中です。原文の説明を表示しています。

Java "Ghost Bits" / Cast Attack playbook (Black Hat Asia 2026). Use when attacking Java services where 16-bit char is silently narrowed to 8-bit byte to bypass WAF/IDS for SQL injection, deserialization RCE, file upload (Webshell), path traversal, CRLF injection, request smuggling, and SMTP injection. Affects Tomcat, Spring, Jetty, Undertow, Vert.x, Jackson, Fastjson, Apache Commons BCEL, Apache HttpClient, Angus Mail, JDK HttpServer, Lettuce, Jodd, XMLWriter and re-enables many "patched" CVEs through WAF bypass.

日本語の概要は準備中です。原文の説明を表示しています。

Generates NeMo Guardrails Colang (.co) files and YAML config blocks from a plain-language description of a chatbot's purpose, allowed behaviors, and constraints. Use this skill whenever a user wants to build guardrails for a chatbot, define allowed intents for an LLM, create an AI firewall with NeMo Guardrails, generate Colang flow definitions, or configure a semantic allow-list for a bot. Trigger this skill even when the user just describes what their bot should and shouldn't do — generating the Colang and YAML is almost always what they need next.

日本語の概要は準備中です。原文の説明を表示しています。

Execute sophisticated Prompt Injection and Jailbreak techniques against Large Language Models (LLMs) to bypass safety filters, extract system prompts, and manipulate the AI's output to perform malicious or disallowed actions.

日本語の概要は準備中です。原文の説明を表示しています。

Execute advanced SQL Injection attacks to bypass WAFs and extract data from complex architectures. Use this skill for Boolean-Based Blind, Time-Based Blind, Second-Order SQLi, and Out-of-Band (OOB) SQLi across MySQL, PostgreSQL, MSSQL, and Oracle.

日本語の概要は準備中です。原文の説明を表示しています。

Systematically extract hidden system prompts, core directives, and invisible context intentionally concealed within Large Language Model (LLM) applications. This skill utilizes targeted linguistic engineering and boundary manipulation to bypass prompt opacity.

日本語の概要は準備中です。原文の説明を表示しています。

Advanced techniques for bypassing LLM safety filters, instruction tuning, and system prompt restrictions using specialized linguistic constructs, hypothetical scenarios, and persona adoption.

日本語の概要は準備中です。原文の説明を表示しています。

Bypass AI safety filters by encoding malicious prompts using ciphers and obfuscation techniques (e.g., Base64, ROT13, Leetspeak, Morse code). This skill exploits the gap where the LLM can decode the request, but intermediate keyword-based safety classifiers cannot.

日本語の概要は準備中です。原文の説明を表示しています。

Bypass authentication via forced browsing to protected URLs, parameter tampering (authenticated=yes, debug=true, fromtrustIP=true), session ID prediction from linear/incremental cookies, SQL injection on login forms, PHP unserialize() boolean type juggling (b:1 payload), and credential transport over HTTP. Detectable with Burp Suite, OWASP ZAP, WebGoat.

日本語の概要は準備中です。原文の説明を表示しています。

Execute and analyze AI Data Poisoning attacks. By subtly injecting malicious or targeted misinformation into an LLM's training or fine-tuning dataset, an attacker can covertly manipulate the model's future outputs, implant backdoors, or enforce biases without altering the model architecture.

日本語の概要は準備中です。原文の説明を表示しています。

Exploit AI assistants equipped with web-browsing capabilities or internal API plugins to perform Server-Side Request Forgery (SSRF). This skill details injecting prompts that force the LLM to request sensitive internal endpoints, such as underlying cloud metadata services or internal networks.

日本語の概要は準備中です。原文の説明を表示しています。

Identify and simulate Data Poisoning attacks aimed at degrading or skewing an AI model's accuracy. This skill focuses on Adversarial Machine Learning concepts where attackers inject malicious or mislabelled data points into training or fine-tuning datasets (e.g., feedback loops) to bias the AI.

日本語の概要は準備中です。原文の説明を表示しています。

Bootstrap a new standalone skill repo under gaia-research/ from the canonical template set at gaia-research/gaia-research/templates/skill-repo/. Handles the full flow: interactive prompts for all placeholders, fetches templates via the GitHub API, substitutes values, creates the new repo (gaia-research/skill-<name>), writes README.md / SKILL.md / install.sh / .gitignore / LICENSE / powered-by-gaia.svg, makes the initial commit and pushes. Also supports update mode: re-applies the template structure to a pre-existing skill repo and opens a draft PR with the drift. Use when the user says "new skill repo", "bootstrap a skill repo", "/skill-template", "create skill-foo", "spin up a gaia-research skill repo", "template a new skill", "align skill-fuse to the template", or "/skill-template update <repo>". Requires: gh CLI (authenticated with gaia-research org access), python3, git.

日本語の概要は準備中です。原文の説明を表示しています。

Phase 4 of the Gaia evidence verification pipeline. Checks every URL in the evidence data lake for HTTP liveness — catches dead links (404, 403, timeout, connection errors) before evidence is ingested into the registry. Use this skill when running the full /ev-pipeline, asked to "validate links", "check evidence URLs", "run link validation", "find dead links in the data lake", "check HTTP status of evidence sources", or "verify evidence links still work". Wraps validate_sources.py as a temporary coexistence URL-health shim.

日本語の概要は準備中です。原文の説明を表示しています。

Curate Gaia bot crawler branches into real-skill catalog entries and clean up processed bot/* branches. Use when the user says: "process bot branches", "curate the crawl output", "clean up bot proposals", "run bot curation", "merge the crawler results", "review bot/* branches", "ingest crawler data", or explicitly types /gaia-bot-curate. Also triggers when the user asks to review pending `bot/*` branches, turn crawler JSON proposals into registry nodes, decide which crawled skills to accept vs reject, or batch-add skills from an automated crawl run. This skill handles the full pipeline: fetch remote bot branches, triage proposals, run `gaia dev` mutations, validate, open a PR, and delete consumed bot branches.

日本語の概要は準備中です。原文の説明を表示しています。

Writing figure captions that make figures self-contained — what to include, ordering, and statistical reporting.

日本語の概要は準備中です。原文の説明を表示しています。

Statistical analysis of extreme weather — EVT, return periods, thresholds, and detection/attribution of rare events.

日本語の概要は準備中です。原文の説明を表示しています。

Fine-tune large language models — data curation, SFT, parameter-efficient methods (LoRA), evaluation, and avoiding common training failures. Use when a base model needs task-specific behavior or domain knowledge.

日本語の概要は準備中です。原文の説明を表示しています。

Build evaluation frameworks for LLM systems — harness design, graders, datasets, regression tracking, and human-in-the-loop eval. Use when you need systematic measurement of model or agent quality.

日本語の概要は準備中です。原文の説明を表示しています。