arXiv (All)
open access
ToolFence: Fine-Grained Authorization for Secure Tool-Using LLM Agents
Tool-using LLM agents remain vulnerable to indirect prompt injection because trusted instructions and untrusted observations share one context, allowing malicious content to steer consequential input-filtering defenses. Multi-path consensus defenses still leave a high attack success rate because the
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- ToolFence: Fine-Grained Authorization for Secure Tool-Using LLM Agents#1122203
- LLM-Based Agents for Software and Systems Security: Approaches, Applications, and Assessment#618499
- Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback#200400
- AgentSecBench: Measuring Prompt Injection, Privacy Leakage, and Tool-Use Integrity in LLM Agents#229449
- TRUSTDESC: Preventing Tool Poisoning in LLM Applications via Trusted Description Generation#2465
Record · ID 1132397
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive