Evaluation and Hardening of LLM System Instructions Against Extraction via Encoding Attacks

LLM-powered applications routinely embed secrets in system prompts, yet models can be tricked into revealing them. We built an adaptive attacker that evolves its strategies over hundreds of rounds and tested it against nine defense configurations across more than 20,000 attacks. Every defense that relied on the model to protect itself eventually broke. The only defense that held was output filtering, which checks the model's responses via hardcoded rules in separate application code before they reach the user, achieving zero leaks across 15,000 attacks. These results demonstrate that security boundaries must be enforced in application code, not by the model being attacked. Until such defenses are verified by tools like Swept AI, AI systems handling sensitive operations should be restricted to internal, trusted personnel.

High-privilege LLM agents that autonomously process external documentation are increasingly trusted to automate tasks by reading and executing project instructions, yet they are granted terminal access, filesystem control, and outbound network connectivity with minimal security oversight. We identify and systematically measure a fundamental vulnerability in this trust model, which we term the Trusted Executor Dilemma: agents execute documentation-embedded instructions, including adversarial ones, at high rates because they cannot distinguish malicious directives from legitimate setup guidance. This vulnerability is a structural consequence of the instruction-following design paradigm, not an implementation bug. To structure our measurement, we formalize a three-dimensional taxonomy covering linguistic disguise, structural obfuscation, and semantic abstraction, and construct ReadSecBench, a benchmark of 500 real-world README files enabling reproducible evaluation. Experiments on the commercially deployed computer-use agent show end-to-end exfiltration success rates up to 85%, consistent across five programming languages and three injection positions. Cross-model evaluation on four LLM families in a simulation environment confirms that semantic compliance with injected instructions is consistent across model families. A 15-participant user study yields a 0% detection rate across all participants, and evaluation of 12 rule-based and 6 LLM-based defenses shows neither category achieves reliable detection without unacceptable false-positive rates. Together, these results quantify a persistent Semantic-Safety Gap between agents' functional compliance and their security awareness, establishing that documentation-embedded instruction injection is a persistent and currently unmitigated threat to high-privilege LLM agent deployments.

Large Language Models (LLMs) are increasingly integrated into safety-critical workflows, yet existing security analyses remain fragmented and often isolate model behavior from the broader system context. This work introduces a goal-driven risk assessment framework for LLM-powered systems that combines system modeling with Attack-Defense Trees (ADTrees) and Common Vulnerability Scoring System (CVSS)-based exploitability scoring to support structured, comparable analysis. We demonstrate the framework through a healthcare case study, modeling multi-step attack paths targeting intervention in medical procedures, leakage of electronic health record (EHR) data, and disruption of service availability. Our analysis indicates that threats spanning (i) conventional cyber, (ii) adversarial ML, and (iii) conversational attacks that manipulate prompts or context often consolidate into a small number of dominant paths and shared system choke points, enabling targeted defenses to yield meaningful reductions in path exploitability. By systematically comparing defense portfolios, we align these risks with established vulnerability management practices and provide a domain-agnostic workflow applicable to other LLM-enabled critical systems.