AgentLSD: Evaluating AI Security Agents Under Adversarial Task Contamination

Matteo Golinelli, Idilio Drago, Matteo Boffa i 2 więcej

[Kryptografia i bezpieczeństwo] Autorzy: Matteo Golinelli, Idilio Drago, Matteo Boffa i 2 więcej

AI agents for security inspect web pages, source code, logs, configuration files, and command outputs. These environments may contain deceptive artifacts that influence the agent's behavior. We call this adversarial task contamination. Whereas prompt injection relies on attacker-supplied instructions, task contamination also includes non-instructional evidence, such as fake results and decoy endpoints. We present AgentLSD, a controlled framework for studying adversarial task contamination. AgentLSD uses Capture the Flag (CTF) challenges as its experimental environment. We inject trap artifacts, such as fake flags, misleading hints, decoy endpoints, and hidden cues, while preserving the intended CTF solution. The framework supports paired clean and trap-augmented experiments with deterministic trap generation, runtime injection, telemetry, and delivery verification. We evaluate six model…

Kategoria arxiv

cs.CR

Kategoria

Kryptografia i bezpieczeństwo

Pdf

https://arxiv.org/pdf/2609.19140v1

Doi

10.1145/3847352.3848111

Otwórz oryginał w źródle ↗