arXiv (All)
open access
Measuring the Permission Gate: A Stress-Test Evaluation of Claude Code's Auto Mode
Claude Code's auto mode is the first deployed permission system for AI coding agents, using a two-stage transcript classifier to gate dangerous tool calls. Anthropic reports a 0.4% false positive rate and 17% false negative rate on production traffic. We present the first independent evaluation of t
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- What Did the Agent Actually Do? Evidence-Grounded Oversight for Long-Horizon Agents#1215509
- GUISpector: An MLLM agent framework for automated verification of natural lananguage requirements in GUI prototypes / Kristian Kolthoff, Felix Kretzer, Simone Paolo Ponzetto, Alexander Maedche, Christian Bartelt#1106512
- Behavioral Integrity Verification for AI Agent Skills#178803
- The CTF is dead, long live the CTF? Exploring perspectives on AI and the recognition of skill in capture-the-flag competitions#1428282
- The CTF is dead, long live the CTF? Exploring perspectives on AI and the recognition of skill in capture-the-flag competitions#1427552
Record · ID 1423827
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive