Author

Igor Santos-Grueiro

View on Semantic Scholar

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Jul 2026

Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agents

A controlled-invalidation suite spanning browser, tool/API, and multi-agent workflows is built, which preserves the user goal and payload shape while invalidating the authority relation before durability, and is a reporting and runtime-design lesson: endpoint success is a utility metric; authorized commit is a security property.

Igor Santos-Grueiro · 6 citations · ⚡1

Preprint Jul 2026

When Binaries Talk Back: Representation-Confusion Attacks on LLM-Assisted Reverse Engineering

Such failures are called Representation-Confusion Attacks in Reverse Engineering (RARE): the pipeline promotes a correctly extracted observation to instruction authority, claim-validating evidence, or trusted analysis state without the authority or support that role requires.

Igor Santos-Grueiro · 0 citations

Preprint Jul 2026

Context-to-Execution Integrity for LLM Agents

Across the evaluated sinks, CXI admits execution only when field, effect, and invocation authority bind to the same action manifest, and across the evaluated sinks, CXI admits execution only when field, effect, and invocation authority bind to the same action manifest.

Igor Santos-Grueiro · 4 citations · ⚡1