TRUSTDESC prevents tool poisoning in LLM applications by automatically generating accurate tool descriptions from code via a three-stage pipeline of reachability analysis, description synthesis, and dynamic verification.
A comprehen- sive overview of large language models.ACM Transac- tions on Intelligent Systems and Technology, 16(5):1–72
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
TRUSTDESC: Preventing Tool Poisoning in LLM Applications via Trusted Description Generation
TRUSTDESC prevents tool poisoning in LLM applications by automatically generating accurate tool descriptions from code via a three-stage pipeline of reachability analysis, description synthesis, and dynamic verification.