Backend
ROPE: Routed Origin Policy Enforcement against Indirect Prompt Injection
arXiv cs.CR0 views
arXiv:2608.27496v2 Announce Type: replace Abstract: Tool-using LLM agents execute consequential operations on behalf of users. Because the LLM driving an agent processes trusted user instructions and untrusted content in the same context, agents are vulnerable to indirect prompt injection attacks that induce unintended actions by mixing malicious instructions into benign data. Defenses based on prompting or content detection are easily evaded by paraphrasing attacks, while system-level defenses that constrain tool calls using inferred user intent, or restrict which sources can supply values to sensitive tools, greatly compromise utility. We present ROPE (Routed Origin Policy Enforcement), a defense that greatly improves the utility-security tradeoff by leveraging system roots of trust to create and enforce per-task policies on sensitive tool parameters. Our key insight is that authentication and integrity protection provide a basis for identifying the source of content independently of instructions embedded in it. Before a task unfolds, an LLM router reads only trusted task input to set a provenance rule for each sensitive tool parameter, accounting for the nature of the task and the values and sources the user specified. As the agent works, an origin labeler records where each piece of content came from, using the user's request, platform metadata, and protected record fields as trust anchors. Before any sensitive tool executes, a deterministic verifier requires each of its origin-guarded values to match a value in a source its rule accepts. We show that ROPE provably guarantees parameter value provenance to sensitive tool calls and is immune to paraphrasing attacks. Against eleven defenses on AgentDojo and AgentDyn under static, adaptive, and long-horizon attacks, ROPE exhibits near-perfect security while compromising far less utility than the best baseline defenses. Code and data are available at https://github.com/xhOwenMa/ROPE.
Source:https://arxiv.org/abs/2608.27496PreviousNo Country for Old Privacy: The Evolving Challenges of Anonymity in BitcoinNextGPUThor: Amplifying Rowhammer Attacks via Non-Uniform Patterns to Exploit ECC-Protected GPUs
Related posts
pytrends trending_searches() returns 404: how to get Google trending searches in Python (2026)
0dev.to
How We Built 225+ Static Developer Tools & Precision Calculators with Next.js Turbopack and 0ms Latency
0dev.to
Claude Code auto mode unavailable or classifier blocked
0dev.to

My MCP Scanner Scored 0 of 2 on a Real CVE. Here Is What Found It Instead
0dev.to
Most of the AI Agents on GitHub Are While Loops in a Trench Coat
0dev.to

The Key Expires in 24 Hours. The Retry Arrives on Monday.
0dev.to