TRUSTDESC: Preventing Tool Poisoning in LLM Applications via Trusted Description Generation

Computer Science > Cryptography and Security [Submitted on 8 Apr 2026] TRUSTDESC: Preventing Tool Poisoning in LLM Applications via Trusted Description Generation Hengkai Ye, Zhechang Zhang, Jinyuan Jia, Hong Hu Large language models (LLMs) increasingly rely on external tools to perform time-sensitive tasks and real-world actions. While tool integration expands LLM capabilities, it also introduces a new prompt-injection attack surface: tool poisoning attacks (TPAs). Attackers manipulate tool descriptions by embedding malicious instructions (explicit TPAs) or misleading claims (implicit TPAs) to influence model behavior and tool selection. Existing defenses mainly detect anomalous instructions and remain ineffective against implicit TPAs. In this paper, we present TRUSTDESC, the first framework for preventing tool poisoning by automatically generating trusted tool descriptions from implementations. TRUSTDESC derives implementation-faithful descriptions through a three-stage pipeline. SliceMin performs reachability-aware static analysis and LLM-guided debloating to extract minimal tool-relevant code slices. DescGen synthesizes descriptions from these slices while mitigating misleading or adversarial code artifacts. DynVer refines descriptions through dynamic verification by executing synthesized tasks and validating behavioral claims. We evaluate TRUSTDESC on 52 real-world tools across multiple tool ecosystems. Results show that TRUSTDESC produces accurate tool descriptions that improve task completion rates while mitigating implicit TPAs at their root, with minimal time and monetary overhead. Subjects: Cryptography and Security (cs.CR) Cite as: arXiv:2604.07536 [cs.CR]   (or arXiv:2604.07536v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2604.07536 Focus to learn more Submission history From: Hengkai Ye [view email] [v1] Wed, 8 Apr 2026 19:18:11 UTC (404 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-04 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)