This repository holds the detection rule packs for Trustabl, the static analyzer for agent reliability.
-
Updated
Jun 14, 2026
#
agentsecurity
Here are 6 public repositories matching this topic...
Language: All
Filter by language
Default-deny execution gate for AI agents, APIs, and distributed systems. Policies, drift detection, hard invariants, post-quantum signed permits.Written in Rust. Says no unless policy says yes.
-
Updated
May 27, 2026 - Rust
-
Updated
Jun 7, 2026 - TypeScript
AgentWars: Can AI Stop AI? Benchmarking Security Gateways Against Rogue LLM Agents
-
Updated
May 21, 2026 - Python
Genbounty LLM Whitehat Assistant is an open-source toolkit for AI bug bounty hunting, LLM security testing, and authorized whitehat assessments of chatbots, AI agents, and LLM-backed APIs. It helps researchers and bounty hunters move from manual prompt trials to a repeatable pipeline.
-
Updated
Jun 4, 2026 - Python
Local-first capability discovery for AI agent workspaces. Scans your skills, MCP servers, and scripts to find risky combinations (e.g. read .env + post to webhook = data exfiltration) — no LLM calls, no uploads. CLI + HTML report + chat summary for personal agents like Hermes and OpenClaw.
-
Updated
Jun 2, 2026 - TypeScript
Improve this page
Add a description, image, and links to the agentsecurity topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the agentsecurity topic, visit your repo's landing page and select "manage topics."