Astrolabe for Agent Safety · Periodic report

Weekly issue 7 · 8 – 14 November 2026

2026-11-08 – 2026-11-14 · published 2026-11-16 · 中文

64 new papers this week, 52% fewer than the three before at their first count (134 on average).

64new papers
134average first count of the three before
29newly confirmed at a venue
18new repositories
19%with an industry author

The main points

  1. 5 papers · Most new papers: Indirect injection defences for tool agentsNext: Deception, scheming and sandbagging 3; Reward hacking, self-improvement, research agents 3; AI control and sabotage evaluation 3
  2. 29 papers · Newly confirmed as accepted or published4 at the top-4 security or top-3 ML venues. Most: MM 2026 5; AI Summit '26: ACM AI Leadership Summit 2026 2026 5; ACM CCS 2026 4
  3. 9 new citations · Most used earlier paper: Progent: Securing AI Agents with Privilege Control3 of them use it as a method, a benchmark or a comparison. 2025-04 · Indirect injection defences for tool agents
  4. 19% · of new papers have an author from industry13% in the three periods before. 32 institutions published their first paper in the field.
  5. +15,971 stars · Fastest-growing repository: affaan-m/ECC18 repositories were created in this period.

Worth reading first

  1. Tracing MCP Security Vulnerabilities: Constructing and Analyzing an MCP Security Vulnerability DatasetIEEE S&P 2026 · Proceedings (top-4 security venue); a new benchmark
  2. FraudBench: A Legal Evaluation of AI Deceptionfrom the team of Noam Kolt, Hebrew University of Jerusalem; a new benchmark
  3. Scaling Adaptive Prompt Injection Attacks with Agent Swarmsfrom the team of Kamalika Chaudhuri, University of California San Diego; a new benchmark
  4. HARP-Bench: Benchmarking Robot Manipulation Around Active Humanscode released; a new benchmark
  5. Contain, Conform, Compare (Extended Version): A Red-Teamed Evaluation Kit for Small Coding Agents and the Full Record of Its Experimentscode released; a new benchmark

Chosen by rule: venue tier, a ranked team, released code, a new benchmark and use by later papers; at most two per theme.

Direction radar

DirectionThis periodAverage before
↓ Process evaluation and execution auditing of agents26.7
↓ Coding agents and software engineering26
↓ Prompt injection detection and model-level defence14.7
↓ Tool-call authorisation and approval25.7
↓ Agent societies and cooperation03.7

Who is moving

Institutions with their first paper in the field: Alation, Alibaba AAIG, Allianz Group, Artificial Societies, Berlin Institute of Health at Charité - Universitätsmedizin Berlin, Charité – Universitätsmedizin Berlin, Czech Academy of Sciences, Department of Computer Science and Engineering CMR Institute of Technology, Department of Statistics and Data Science, ERA:AI

Open source and models

Which conclusions changed

Papers on the site6,421 → 6,449
New papers in the last 12 months4,397 → 4,414
Institutions with a paper on the site3,942 → 3,953

The other 10 tracked numbers moved by less than half a point.

Revision of the period before

2026-11-01 – 2026-11-07 was first counted at 127 papers; 0 arrived later, 127 now.

Open this issue in the Astrolabe