
mcp-attack-detection-sentinel
Sentinel detection lab for MCP attack chains: CVE-2026-26118 SSRF token theft, tool poisoning, cross-server exfiltration, identity post-exploitation.…

Sentinel detection lab for MCP attack chains: CVE-2026-26118 SSRF token theft, tool poisoning, cross-server exfiltration, identity post-exploitation.…

Multi-layered prompt injection detector for AI applications using heuristics, LLM-based analysis, vectorDB attack signatures, and canary token leak…

Benchmark for evaluating safety risks of computer-using agents, with 104 realistic misuse scenarios across seven malicious categories, supporting…

Embed multiple secret messages in LLM chat token choices using arithmetic/Discop steganographic coders, with bit-exact decoding and steganalysis…

Experiments for control-token chain-of-thought suppression and parser-leniency attacks on tool-using LLM agents

Security Advisory: Stored Cross-Site Scripting Via Agent Messages Leading To Session Token Theft (openclaw-dashboard)

Secure agents in seconds with permissions enforced at runtime.

Evades LLM text watermarks by injecting Unicode variation selectors; includes the SynthID generator, mean-g detector, normalization defenses, and…