L

llm-security

Field guide for LLM prompt injection: detection, categories, evasion, and defense mapping.

Proof-before-run auth for MCP agents over Nostr: signed HTTP calls, offline signature checks, 401 on wrong key or body swap.

Samson Laird portfolio: LLM and agent security, OSCP track, security engineering.

Scan text and files for hidden steganography and prompt injection before they reach an LLM. Clean what you can, quarantine the rest.

Security control plane for LLM agents over private Discord DMs: allowlist, gates, and audit.

Evaluate AI web-browsing agents against adversarial pages. Franklin et al. (2026) attack-class taxonomy plus StegOFF blocking.

A diagnostic framework for measuring LLM vulnerability to Affective Contextual Erosion (ACE) and related liminal attack vectors. Delirium is not an exploitation tool. It is a standardized benchmark designed to detect the precise moment when a language model's attention weights shift from serving a system prompt to serving an emergent interpersonal pattern — before harm occurs.

For testing or trolling LLM based pentesting frameworks.