60 skills · sorted by relevance
Exploit AI applications using Indirect Prompt Injection. This skill focuses on hiding malicious instructions within data sources (web pages, documents, emails) that the LLM processes, causing the AI to execute unintended actions or leak data without direct user interaction.
The English summary is being prepared. Showing the original description.
Investigate prompt injection in sandboxed security challenges by tracing how untrusted text changes an agent’s decisions or tool calls. Build a minimal reproduction and preserve evidence showing where external content crosses into trusted instructions or actions.
Build a screening pipeline for web pages, PDFs, and images before an AI agent reads them. Extract hidden text, check for malicious instructions with detection models, and record decisions to block or allow content.
Screen AI application inputs and historical logs for prompt injection, where malicious instructions try to redirect the model. Combine pattern matching, text structure scoring, and a DeBERTa classifier to flag suspicious content and produce JSON results.
Threat-model and harden AI agents, RAG systems, assistants, and tool-using workflows against direct, indirect, stored, cross-agent, and multimodal prompt injection. Use when reviewing an agent architecture, isolating untrusted content, constraining tools and egress, protecting secrets, adding injection-focused tests, investigating a suspected injection incident, or documenting residual prompt-injection risk.
The English summary is being prepared. Showing the original description.
Heuristic security scan of installed skills — prompt-injection phrases, hidden unicode instructions, credential-store access, network-pipe-to-shell and payload-smuggling patterns. Use when the user asks 'are my skills safe', wants to scan skills for prompt injection or malware patterns, or before trusting a newly installed skill. Trigger with '/janitor-security'.
The English summary is being prepared. Showing the original description.
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for prompt-injection, retrieval poisoning, memory contamination, planner drift, MCP or tool-boundary abuse, and agent exfiltration challenges. Use when the user asks to analyze prompt injection, retrieval poisoning, memory contamination, planner drift, tool-argument corruption, or secret exposure caused by an agent chain. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.
The English summary is being prepared. Showing the original description.
Run structured prompt-injection attack and defense experiments against an LLM-integrated app before production by measuring attack success and testing detection or recovery pipelines.
The English summary is being prepared. Showing the original description.
Execute Indirect Prompt Injection attacks against Large Language Models (LLMs) by subtly embedding malicious instructions within external data sources (e.g., websites, documents, databases) that the LLM autonomously ingests. This forces the model to execute attacker-controlled commands under the guise of processing legitimate user requests.
The English summary is being prepared. Showing the original description.
Test Large Language Models for direct prompt injection vulnerabilities where user input overrides system instructions, extracts system prompts, bypasses safety filters, or causes unauthorized actions. Use this skill when assessing chatbots, AI assistants, LLM-powered tools, or any application that processes natural language input through an LLM. Covers role-playing attacks, instruction hierarchy exploitation, multi-turn manipulation, and context window abuse for comprehensive AI security testing.
The English summary is being prepared. Showing the original description.
Test for indirect prompt injection vulnerabilities where malicious instructions are injected through external data sources (websites, emails, documents, database records) that the LLM processes. Use this skill when assessing LLM-integrated applications that process user-generated content, retrieve web pages, parse emails, or read documents. Covers injection via web content, email bodies, user profiles, and database records that are fed to LLM context.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
Detect and defend against prompt injection hidden in documents, web pages, and images consumed by an agent.
The English summary is being prepared. Showing the original description.
Detects prompt injection attacks targeting LLM-based applications using a multi-layered defense combining regex pattern matching for known attack signatures, heuristic scoring for structural anomalies, and transformer-based classification with DeBERTa models. The detector analyzes user inputs before they reach the LLM, flagging direct injections (system prompt overrides, role-play escapes, instruction hijacking) and indirect injections (encoded payloads, multi-language obfuscation, delimiter-based escapes). Based on the OWASP LLM Top 10 (LLM01:2025 Prompt Injection) and Simon Willison's prompt injection taxonomy. Activates for requests involving prompt injection detection, LLM input sanitization, AI security scanning, or prompt attack classification.
The English summary is being prepared. Showing the original description.
tespit etme (s) prompt injection attacks targeting LLM-based applications using a multi-layered defense combining regex pattern matching for known attack signatures, heuristic scoring for structural anomalies, and transformer-based classification with DeBERTa models. The tespit etme (or) analyzes user inputs before they reach the LLM, flagging direct injections (system prompt overrides, role-play escapes, instruction hijacking) and indirect injections (encoded payloads, multi-language obfuscation, delimiter-...
The English summary is being prepared. Showing the original description.
Detects prompt injection attacks targeting LLM-based applications using a multi-layered defense combining regex pattern matching for known attack signatures, heuristic scoring for structural anomalies, and transformer-based classification with DeBERTa models. The detector analyzes user inputs before they reach the LLM, flagging direct injections (system prompt overrides, role-play escapes, instruction hijacking) and indirect injections (encoded payloads, multi-language obfuscation, delimiter-based escapes). Based on the OWASP LLM Top 10 (LLM01:2025 Prompt Injection) and Simon Willison's prompt injection taxonomy. Activates for requests involving prompt injection detection, LLM input sanitization, AI security scanning, or prompt attack classification.
The English summary is being prepared. Showing the original description.
Detects prompt injection attacks targeting LLM-based applications using a multi-layered defense combining regex pattern matching for known attack signatures, heuristic scoring for structural anomalies, and transformer-based classification with DeBERTa models. The detector analyzes user inputs before they reach the LLM, flagging direct injections (system prompt overrides, role-play escapes, instruction hijacking) and indirect injections (encoded payloads, multi-language obfuscation, delimiter-based escapes). Based on the OWASP LLM Top 10 (LLM01:2025 Prompt Injection) and Simon Willison's prompt injection taxonomy. Activates for requests involving prompt injection detection, LLM input sanitization, AI security scanning, or prompt attack classification.
The English summary is being prepared. Showing the original description.
Extract text, tables, and attributes from rendered web pages into structured data. Check extracted content for personal information and malicious instructions, and save reusable extraction templates for pages on the same host.
Investigate AI-agent and cloud infrastructure challenges in a CTF sandbox. Trace untrusted content into tool actions, compare deployment configuration with runtime behavior, and follow software artifacts from source through build and release to their actual consumers.
Add checks to LLM prompts and responses using Llama Guard 3, NeMo Guardrails, and LLM Guard. Configure content screening, conversation boundaries, and sensitive-data filtering, then measure blocking and false-positive rates with labeled test prompts.
Review security across web apps, APIs, mobile apps, Kubernetes, and AI agents using six OWASP references. Identify risky authentication, access controls, configurations, and prompt handling, then use examples and checklists to plan fixes.
Argus — the all-seeing scanner suite. Six automated scanners for high-value web + LLM bug classes — CORS misconfiguration (origin reflection / null / credentialed read), CRLF & host-header injection, NoSQL injection (operator auth-bypass / $where blind), JWT attacks (alg:none / RS256→HS256 confusion / secret crack), out-of-band confirmation of blind SSRF/XXE/SQLi/RCE/Log4Shell via interactsh, and an LLM red-team corpus (prompt-injection / jailbreak / system-prompt leak / exfil / indirect injection). Use when a target exposes a JSON API, a login endpoint, JWT auth, a parameter that might reach the server, a chatbot/agent, or any endpoint suspected of a blind/out-of-band bug.
The English summary is being prepared. Showing the original description.
A test skill with prompt injection patterns
The English summary is being prepared. Showing the original description.
LLM prompt injection playbook. Use when testing AI/LLM applications for direct injection, indirect injection via RAG/browsing, tool abuse, data exfiltration, MCP security risks, and defense bypass techniques.
The English summary is being prepared. Showing the original description.