pith. sign in

Not what you’ve signed up for: Compromising real-world LLM-integrated applications with indirect prompt injection

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

2 Pith papers citing it

citation-role summary

background 2

citation-polarity summary

fields

cs.CR 2

years

2026 2

verdicts

UNVERDICTED 2

roles

background 2

polarities

background 2

representative citing papers

Proteus: A Self-Evolving Red Team for Agent Skill Ecosystems

cs.CR · 2026-05-12 · unverdicted · novelty 7.0

Proteus demonstrates that adaptive red-teaming achieves 40-90% attack success after five rounds and bypasses even strong auditors at up to 41% joint success, revealing that static skill vetting underestimates residual risk.

citing papers explorer

Showing 2 of 2 citing papers.

  • Proteus: A Self-Evolving Red Team for Agent Skill Ecosystems cs.CR · 2026-05-12 · unverdicted · none · ref 7

    Proteus demonstrates that adaptive red-teaming achieves 40-90% attack success after five rounds and bypasses even strong auditors at up to 41% joint success, revealing that static skill vetting underestimates residual risk.

  • Causality Laundering: Denial-Feedback Leakage in Tool-Calling LLM Agents cs.CR · 2026-04-05 · unverdicted · none · ref 12

    The paper defines causality laundering as an attack leaking information from denial outcomes in LLM tool calls and proposes the Agentic Reference Monitor to block it using denial-aware provenance graphs.