Tool
provenance-gate/posts/01-provenance-vs-detection.en.md at main · Yehielamor/provenance-gate
Publication date not yet evaluated · Added github.com
Page published
Coverage timeline
Single-source research — one report is available.
Why it matters
provenance-gate offers defenders a detection-free, provenance-based approach to stopping prompt-injection-driven tool abuse in agentic systems, addressing the well-documented brittleness of classifier-based prompt-injection defenses.
The provenance-gate project publishes a deterministic tool gateway that sits between an AI agent and its tools and, rather than reading or classifying injected text, tracks the provenance of each value in a tool call (recipient, IBAN, URL, amount). In evaluation on AgentDojo (assuming the model is always hijacked), the gateway blocked 99.3% of 609 hijacked attacks and held steady against reversed, base64, invisible-Unicode-tag, and machine-translated obfuscations, while three open prompt-injection classifiers showed high false positives and poor detection of obfuscated injections.