AGAS
phkhanhtrinh23/agasLLM-driven agentic group shilling attack framework that manipulates black-box collaborative-filtering recommender rankings using adaptive multi-role…
adversarial-attackai-securityeducation+2
2
phkhanhtrinh23/agasLLM-driven agentic group shilling attack framework that manipulates black-box collaborative-filtering recommender rankings using adaptive multi-role…
arcanum-sec/wraithBrowser-hooking framework for authorized red teams and educators. Hooks browsers via XSS, provides interactive post-exploitation control, blind-XSS…
safeagent-beihang/clawguardEnterprise AI agent security toolkit providing pre-flight auditing, configuration hardening, runtime threat detection, and active defense against…
geeksikhsecurity/ai-tool-poisoning-guardFree security-baseline rule for Claude Code, Codex, and Cursor: treats MCP tool descriptions as untrusted input (OWASP MCP Top 10 MCP03,…
pvharmo2/gha-lab-733c168b88Reproduces CVE-2026-44246, a prompt injection vulnerability in nnU-Net's GitHub Actions triage agent, demonstrating how issue content is inlined into…
fknmega/aetherAutonomous AI Driven OSINT & security-research desktop agent (macOS/Windows) that builds a live knowledge graph. Authorized use only
mouteee/autonomous-offensive-llm-handbookA deterministic harness and handbook for autonomous offensive LLM agents, enforcing authorization, scope, and evidence gates to ensure reproducible…
ghostwolflab/ai_security_topA structured knowledge base covering AI security fundamentals, threat modeling, red team offensive techniques, and blue team defenses, including LLM…
db-ol/cuaharmBenchmark for evaluating safety risks of computer-using agents, with 104 realistic misuse scenarios across seven malicious categories, supporting…
nanda-rani/safeA contextual security auditing system for research artifacts
qkrrkd90-source/weavemarkReference implementation of a multi-bit LLM watermarking scheme using coded payload spreading, unbiased reweighting, and soft-decision ECC decoding…
cucu220123/safety-awarenessResearch code for extracting and training safety-awareness directions in multimodal LLMs to improve refusal behavior while limiting benign-task drift.
xhowenma/ropeDefense framework enforcing routed origin policy to prevent indirect prompt injection in tool-using LLM agents, with deterministic origin checks and…
jaewonalive/camodocsResearch implementation of a poisoning attack against retrieval-augmented language models using camouflaged documents to evade filtering defenses and…
ai45lab/skill-safety-benchBenchmark for evaluating AI agent safety against attacks embedded in skill-facing context, with 155 cases across 6 risk domains, measuring task…
x1nons/claude-xml-injectionTechnical disclosure: Credential fabrication via XML tag injection in Claude Sonnet 4.6. Reported June 14 2026, patched June 20 2026.
d-diaa/swordstampSemantic Watermarking with Order-Robust Detection over Sub-sentence Units
vxssroott/cve-2026-78906-chatgpt-prompt-injectionAI Infrastructure Vulnerability Research. CVE-2026-78906: Prompt injection and memory exfiltration in OpenAI's ChatGPT API.