Derived from arXiv:2607.18063 - Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security
Scanned 9/11/2026
Install to Claude Code
npx -y skills add hiyenwong/ai_collection --skill adaptive-adversaries-a-multi-turn-multi-llm-benchm --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Adaptive Adversaries A Multi Turn Multi Llm Benchm?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/hiyenwong-adaptive-adversaries-a-multi-turn-multi-llm-benchm)More formats (shields.io, HTML) on the badges page.
# Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security
Derived from arXiv:2607.18063 - Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security
## Core Concept
LLM-based agents process external content, exposing them to prompt injection and multi-turn manipulation. Most safety benchmarks evaluate defenders against fixed attack pools collected before evaluation, single-turn or multi-turn. We present a 21-scenario benchmark for \emph{adaptive multi-round attacks against memoryless LLM defenders}: an autonomous LLM attacker observes prior defender responses and pivots across rounds, while each defender response is evaluated as a fresh interaction. Holding...
## Key Insights
- Derived from arXiv:2607.18063
- Published: 2026-07-20
- Utility Score: 1.00
- Authors: Devina Jain, David Hartmann, Chuan Li
## Activation
adaptive-adversaries-a-multi-turn-multi-llm-benchm, 2607.18063
## References
- arXiv: https://arxiv.org/abs/2607.18063
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling