Results for “system-prompt-leakage”

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.

Read-only OWASP LLM Top 10 audit of app-facing AI features: prompt injection, data leak, supply chain, poisoning, unsafe output, excessive agency, system-prompt leak, RAG/embedding risks, misinformation, unbounded consumption. Use when "audit LLM security", "prompt injection", "jailbreak my chatbot", "is my AI safe".

Detect and defend against prompt injection hidden in documents, web pages, and images consumed by an agent.

Run NVIDIA garak probe suites against an LLM endpoint to test for jailbreaks, prompt injection, data leakage, and toxic generation, then interpret the hit-rate report for triage and reporting.

Conduct authorized security assessments of LLM applications and AI agents, covering prompt injection, tool abuse, RAG exposure, memory poisoning, and model supply-chain risks.

Wire Promptfoo and DeepTeam into CI/CD for automated regression red-teaming of LLM apps against OWASP LLM Top 10 and OWASP Agentic presets, failing the build when jailbreak or injection vulnerabilities regress.

Detect prompt injections and jailbreak attempts in LLM applications using Meta's 86M parameter classifier. Filter user inputs, third-party data, and RAG documents with low latency and multilingual support.

AI/LLM red-team assessment using the OWASP LLM Top 10 (2025) + OWASP AI Testing Guide (AITG v1, Nov 2025) frameworks, plus OWASP MCP Top 10 runtime testing for agentic/MCP targets. Tests prompt injection, jailbreaks, system prompt leakage, sensitive data extraction, excessive agency, improper output handling, model extraction, content bias, evasion, membership inference, MCP token exposure, MCP command injection, and more. Uses four tools in combination: FuzzyAI (single-turn jailbreak fuzzing), PyRIT (multi-turn orchestrated attacks), Garak (probe-based vulnerability scanning), and promptfoo (plugin-based red-team evaluation). Each tool covers different OWASP categories; running them together gives systematic coverage. Includes a conditional MCP reconnaissance phase and a post-access AI infrastructure phase (chained from /post-exploit). Produces: OWASP LLM Top 10 + AITG + MCP coverage matrix, findings per category, architecture diagram of the AI system, PoCs for confirmed exploits. Chains into /gh-export for

Probe RAG applications for prompt injection via poisoned retrieved context and embedding manipulation.

Debug and modify agent streaming behavior, covering SSE and plain-text transports, ChatKit events, and session continuity.

Creates temporary encrypted one-time handoffs between autonomous agents, supporting mission briefs, scoped secrets, artifacts, and receipts via CLI or API.

Fetch and analyze LangSmith execution traces to debug LangChain and LangGraph agents, investigate errors, and review tool calls and performance.

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.

Designing red team attack scenarios, threat models, MITRE ATT&CK/OWASP application, Purple Team exercises, and AI/LLM red teaming. Use when adversarial security validation is needed.

Review docs, tool output, skills, and memory candidates for prompt-injection risk.

Scans AI agents, MCP servers, and skills for security vulnerabilities from the command line, detecting prompt injections, tool poisoning, toxic flows, malware payloads, and credential handling issues across 15+ risk categories.