Pith. sign in

PromptSleuth: Detecting Prompt Injection via Semantic Intent Invariance.arXiv preprint arXiv:2508.20890, 2025.https://arxiv.org/ abs/2508.20890

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CR 2

years

2026 2

representative citing papers

A Security Analysis of the OpenClaw AI Agent Framework

cs.CR · 2026-03-29 · conditional · novelty 6.0 · 2 refs

Security analysis of OpenClaw reveals composable RCE paths from LLM tool calls, invalid closed-world assumptions in exec allowlists, and plugin-based attacks that bypass runtime policy.

citing papers explorer

Showing 2 of 2 citing papers.