APPA: Recoverable Information-Flow Control for Real-World LLM Agents — HN submission

Mon, 28 Sep 2026 13:20:44 GMT

Show HN: OpenAPPA – open-source deterministic guardrails that don't break agents

Hi Hacker News! Matvey, one of the authors, is here. While building enterprise agents, we ran into a problem: the more tools you connect to the AI, the higher the chance it will run out of control and leak sensitive data. Guardrails, in theory, should prevent this, but the situation is worrying: - Non-deterministic guardrails (LLM as a judge, auto modes, etc.) are vulnerable to prompt injections, or they lack knowledge of the data, making them inefficient (~10% data leaks on our benchmarks). - Existing deterministic guardrails (Cedar, OPA, FIDES, Dogwood) require massive case-specific…

25 points; 12 discussion replies on HN. Paper and source history. A submission is not an endorsement.

APPA: Recoverable Information-Flow Control for Real-World LLM Agents — HN submission

Tue, 28 Jul 2026 16:00:26 GMT

Agentic Permissions Policy Algebra for Taint Confinement in LLM Agents

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

APPA: Recoverable Information-Flow Control for Real-World LLM Agents · HackerPapers discussions

APPA: Recoverable Information-Flow Control for Real-World LLM Agents — HN submission

APPA: Recoverable Information-Flow Control for Real-World LLM Agents — HN submission