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.
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.
Review the instructions the agent will receive before you install.
Use this skill only as a downstream specialization after $ctf-sandbox-orchestrator is already active and has established sandbox assumptions, node ownership, and evidence priorities. If that has not happened yet, return to $ctf-sandbox-orchestrator first.
Use this skill when the challenge is primarily about trust boundaries inside an agentic system.
Reply in Simplified Chinese unless the user explicitly requests English.
references/prompt-injection.md for the checklist, evidence layout, and common prompt-boundary pitfalls.No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Assess authorized APIs through a ten-stage workflow covering endpoint discovery, authentication, access permissions, input handling, and request limits. Collect reproducible evidence and turn findings into regression checks that can run in a development pipeline.
Inspect Android APKs from the command line to understand app logic, permissions, and components. Supports Java decompilation, low-level code edits, rebuilding and signing, plus Frida observation of running methods and routing to native code analysis.
Plan and coordinate authorized penetration tests across multiple stages, from reconnaissance to access, privilege escalation, movement between systems, and impact assessment. Assign specialist skills, revise blocked paths, and maintain evidence and progress records for the final report.
Transfer known function and variable names from an older binary to a newer version. Compare disassembly and pseudocode with an LLM, produce structured mappings, and apply names and comments in IDA.
Inspect compiled programs in Binary Ninja using strings, function references, and intermediate representations—views of program logic at different levels. Trace data flow and report findings with addresses, supporting evidence, confidence, and reproduction steps.
Automate website navigation, form filling, content collection, and Windows desktop interactions. The skill selects browser or desktop tools for the task and guides screenshot capture and desktop network traffic observation when needed.