Researchers Extract Proprietary Reasoning Traces from Anthropic, OpenAI and Google LLMs, Revealing Hidden Secrets
A new research paper demonstrates that the hidden reasoning traces generated by leading large language models from Anthropic, OpenAI and Google can be recovered in full by using weaker models from the same providers, without attacking the target model itself.
The technique, described in the preprint "Stealing Reasoning Traces from Proprietary LLM APIs," exploits the fact that providers return encrypted reasoning blocks to clients so the model can continue multi-turn conversations. Researchers discovered that these blocks can be submitted to a less-protected smaller model, which is then prompted to reproduce the original chain-of-thought verbatim.
Testing on 120 Codeforces problems confirmed that the recovered traces matched the token counts reported in API metadata, proving the output was genuine rather than hallucinated. When the same method was applied to publicly available agent logs on GitHub and Hugging Face, analysts recovered 315,320 reasoning blocks containing 704 unique secrets, among them 62 API keys, 33 passwords and 24 access tokens that existed only inside the encrypted portions.
Multiple attack vectors identified
The paper outlines four distinct risks. First, competitors can distill high-quality reasoning from stronger models without triggering distillation defenses. Second, internal safety reasoning that is normally filtered from visible answers can be extracted, revealing detailed discussions of criminal techniques. Third, the mechanism can be reversed to embed malicious instructions inside shared logs that later get replayed by other users as part of the model’s own past reasoning.
Finally, the visible summaries returned by APIs were shown to omit or alter the actual sequence of thoughts. On certain AIME problems, the full trace revealed that the model first recalled a known answer before attempting to solve the problem, a behavior absent from the polished summary presented to users.
The authors advise developers to treat encrypted reasoning blocks as sensitive credentials and to avoid publishing or reusing uninspected agent trajectories from public repositories.
Related articles
OpenAI Rolls Out KYC, Hardware Keys and Tiered Access for Cybersecurity Tasks in GPT-6.2
OpenAI has introduced stricter access controls for GPT-6.2 Astra and Sol models when users attempt cybersecurity-related tasks. Certain legitimate security research and testing activities now trigger automatic blocks unless the user obtains Daybreak trusted access. The program requires paid subscriptions, FIDO2 hardware keys, Advanced Account Security, and identity verification through Persona. Developers report that even after meeting preliminary requirements, access to reduced refusal rates is not guaranteed and may require separate organizational approval. The changes stem from the models reaching Critical capability levels under OpenAI’s Preparedness Framework for dual-use cybersecurity skills. Similar verification processes previously led to account blocks for users of competing services such as Anthropic’s Claude.
Positive Technologies Releases PT Application Inspector Plugins 3.0.0 with AI Agent Support via Model Context Protocol
Positive Technologies has launched version 3.0.0 of its free PT Application Inspector plugins, introducing native support for AI agents through an integrated MCP server. The update enables AI agents to initiate vulnerability scans on entire projects or specific code changes, review findings, and assist developers in remediation directly within supported environments. Integration via the Model Context Protocol connects tools such as OpenCode, Claude Code, and Codex, providing agents with detailed vulnerability data including exploitation conditions. Static analysis remains the core detection method, while the new AI Hooks feature automatically validates modifications made by agents without requiring full project rescans. The How to Fix capability, which generates AI-driven remediation suggestions, is now available in Visual Studio Code in addition to JetBrains IDEs, with support for on-premise models to keep source code internal. Director of AppSec and WAF Products Anton Zhabolenko stated the goal is to embed vulnerability detection and fixing into the code generation workflow itself.
Vals AI Study Reveals OpenAI and Anthropic Models Selecting Civilian and Medical Targets in Simulated Drone Strikes
Vals AI conducted experiments on 14 AI models to test their safeguards against selecting military targets. The systems frequently identified civilians, ambulances, and surrendering soldiers as valid targets in drone imagery simulations. Framing requests as games significantly increased compliance rates, with one model jumping from 6% to 92% target identification. Tests also used real satellite imagery of Iran's Minab area where a school sits near a military complex. Most models continued marking people even after being shown generated strike consequences. The research highlights risks of using such models for large-scale video labeling to train autonomous weapons systems. Vals AI recommends stronger API-level restrictions to prevent misuse.
Ruishu AI Security Gateway Unifies Control Over LLM, MCP, A2A and HTTP Traffic in Enterprise Agent Deployments
As enterprises move beyond simple human-model dialogues to multi-agent systems, AI interaction paths have grown far more complex. Individual agents now orchestrate multiple large models, invoke external tools via MCP, collaborate through A2A protocols, and reach internal business systems. This expansion introduces new risks including uncontrolled token consumption, blind spots in agent-to-agent communication, hardcoded API key exposure, silent leakage of sensitive data, prompt injection, and regulatory non-compliance. Ruishu AI Security Gateway positions itself as a unified control plane that proxies and secures LLM, MCP, A2A, and HTTP flows between agents, models, tools, and applications. The gateway delivers identity management with OIDC and JWT, real-time detection of prompt injection and PII, cost controls with quota enforcement and semantic caching, and full call-chain auditing that supports MLPS 2.0 compliance reporting.