alignment-cage-challenge-2
itm-kitware/alignment-cage-challenge-2CybORG CAGE 2 environment updated for the paper "Alignment of Autonomous Cyber Defense Agents via Adaptive Policy Shaping"
ai-securitydefensive-toolseducation+6
itm-kitware/alignment-cage-challenge-2CybORG CAGE 2 environment updated for the paper "Alignment of Autonomous Cyber Defense Agents via Adaptive Policy Shaping"
maureille/agentic-pcapBenchmark code and interactive results for autonomous network-attack detection by tool-using LLM agents investigating raw PCAPs.
owasp/agentic-evidenceOWASP reference project for agentic AI security evidence: correlates agent execution, identity, tool calls, and authorization decisions into…
owasp/the-agents-epistemic-baggageAn audit-oriented risk model for how agent-generated inferences can change epistemic status, gain operational authority, and influence later…
asngs/agenttriage-open-sourceCross-agent tracing and security-diagnosis system for tool-using LLM agents: normalizes trace events, builds provenance graphs, extracts…
pixee/compaction-launderingSecurity research on context compaction in coding agents: shows how forged role labels in untrusted content survive summarization and get executed,…
peach-research-lab/authorizationbench[🎖️ Honorable Mention in HAIPS @COLM'26] The first benchmark to evaluate how well do LLM agents act in alignment with their assigned authorization…
cosmosyi/autocontrol-arenaAutomated framework for frontier AI safety evaluation that synthesizes executable, pressure-rich test environments to uncover latent risks in…
yxf203/defense-as-skillRuntime guard skill that detects and blocks malicious skill-induced attacks in skill-augmented agents, with an MCTS loop that evolves the guard…
kaandemir993/overlord-rat-reverse-engineering-a-go-based-rat-injection-keylogging-c2-exfiltration-analysisFull static & memory analysis of Overlord RAT: Go agent architecture, HTTP/2 + WebSocket C2, reflective DLL injection, browser keylogging, and IOCs.…
moontea0416/webmirageAdversarial image attacks on vision-language web agents, from visual grounding to browser execution
graph-com/cka-agentResearch implementation of an LLM jailbreak agent that bypasses commercial model guardrails using harmless prompt weaving and adaptive tree search.
uiuc-kang-lab/persistbdResearch code for training adapters that make LLM agent backdoors survive benign fine-tuning, with trigger-rate scoring, SWE-bench evaluation, and…
deep-jlu/skillpoisonResearch pipeline that constructs verified successful experiences and organizes them into formation records to progressively poison model skills via…
zhengxr930/apex_officialDefender framework for LLM agent security that compiles task contracts, validates capability manifests, and checks effects via PLANT/WRAP proof…
lzwhehe/benign-instruction-benchRe-evaluating prompt-injection detectors on LLM agent tool outputs (paper draft, scripts, scores)
wvllxe/cve-2026-104051-pictshare-info-disclosureSensitive info disclosure via info API in PictShare < 3.7.1 (CWE-522). PoC + advisory writeup.
euph00/zoneclaw-codeBenchmark and defense code for persistent memory attacks on OpenClaw-style computer-use agents, with memory-zoning mitigation, attack scenarios, and…