Per-Component Agent Skill Fingerprinting
Arxiv
pdf
2026-06-01T00:00:00
arXiv Paper — PDF not available.
Only the Executive Summary is available here. To read or download the full paper, visit the
arXiv abstract page.
Abstract
AI agents increasingly acquire and execute skills at runtime: bundles of prompt instructions, executable code, and tool declarations fetched from marketplaces and other agents. Governing them needs a stable notion of skill identity, yet cryptographic hashing is engineered to destroy the very similarity we need, as a one-character edit scrambles the digest. We present a compact, locality-sensitive fingerprint that embeds each component of a skill and projects it to bits with a multibank SimHash, giving a fixed 120-byte signature compared in constant time by Hamming distance.
Loading executive summary...