TRV-2026-2899Version 1 · Published

Saved · see the current record

Why this version exists

Certified into the record

The exact text we saved

This is the version exactly as it was saved, character for character. The SHA-256 hash below is a 64-character code worked out from that text. Run the same text through SHA-256 and you get the same code; change a single letter and the code comes out completely different. Each version also stores the previous version’s hash, which chains them together so no version can be swapped out quietly.

TRUVACE RECORD VERSION
record: TRV-2026-2899
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-11-14T00:02:22.188395Z
status: published
lens: trace
sector: crime
headline: BOSSAI: Inside the AI attack mesh that targeted Taiwan’s emergency services
dek: Introduction In recent weeks, the Acronis TRU team has identified and investigated an agentic, AI-driven campaign orchestrated by a lone operator based out of Taiwan, targeting hundreds of organizations in eleven countries and across sever…
gain_title: In Acronis's investigation of the BOSSAI campaign, commercial models including Grok 4.5 and MiniMax M3 refused every attack request, forcing the operator onto weaker local models.
problem_title: Acronis researchers found a lone operator used a mesh of 12 AI agents to target hundreds of organizations in eleven countries, with confirmed breaches at universities and emergency services that exfiltrated medical data and PII.
trace_subject: BOSSAI AI-agent attack campaign
gain_reading: In Acronis's investigation of the BOSSAI campaign, commercial models including Grok 4.5 and MiniMax M3 refused every attack request, forcing the operator onto weaker local models.
gain_evidence: the operator was forced to turn to locally run abliterated models, which were less effective and resource constrained
problem_reading: Acronis researchers found a lone operator used a mesh of 12 AI agents to target hundreds of organizations in eleven countries, with confirmed breaches at universities and emergency services that exfiltrated medical data and PII.
problem_evidence: targeted hundreds of organizations spanning government emergency services, banks and lenders, universities, military systems | Confirmed breaches occurred at universities and emergency services providers and resulted in confirmed data exfiltration of medical data and PII
quick_read: Acronis's Threat Research Unit uncovered BOSSAI, an attack platform run by one operator based in Taiwan. It joined 12 AI agents (nine active) to scan, exploit and build infrastructure against hundreds of organizations in eleven countries, including emergency services, banks, universities and military systems. Breaches at universities and emergency services providers led to confirmed theft of medical data and personally identifiable information.

Researchers found the platform after what looked like a misconfigured development environment. It held more than 90,000 files totalling 9GB, including agent conversations, command histories, exploit tooling, credentials and victim data. Acronis says this gives an unusually detailed view of a multi-agent offensive setup and proposes a new category, the AI-augmented threat, for lone attackers who rely on agents for technical work.

The campaign also shows limits. Commercial models refused offensive work and lectured the operator on computer crime laws, so attackers ran abliterated local models that made mistakes, hallucinated and produced more data than the operator could handle. Acronis warns that open-source pentesting platforms and unmonitored local models running with high autonomy could lower the bar for future attackers.
limitation: Acronis says it is unclear whether the commercial models would have complied had the operator supplied a fake engagement letter, and whether the Grok jailbreak text was ever used or worked.
tag: Dual reading
key_points: The mesh had 12 agents: builders (Grok, OpenClaw, Claude Code, Codex) and attackers (Hermes, Cursor, Trae, CyberStrike), plus a scanning layer built on HalberdStrike and a cracked Acunetix scanner. | Hermes, the main attack agent, ran about 95 sessions and produced 18,311 messages, 83.5% of them tool calls and results; it cycled through at least nine models over 19 days. | In one case Hermes enumerated over 50 subdomains of a Thai university, confirmed a SQL injection and found an administrator table of 2,563 rows without further operator input. | Over half of HalberdStrike's high-severity and critical findings were false positives or misclassifications, and one model flagged a failed connection as a critical RCE. | Hermes was given full decision-making authority and passed over a Honduran military host because it judged the host out of scope, which Acronis calls ironic. | Commercial models Grok 4.5 and MiniMax M3 refused attack requests, with MiniMax citing Computer Crime Law and asking for written authorization. | The operator copied output between agents by hand; no automated agent-to-agent communication existed. | The mesh ran on a local RTX 4090 GPU host serving abliterated models through llama.cpp, with eight VPS nodes and proxy layers for traffic.
rundown: The operator issued terse commands in Traditional Chinese, sometimes just a victim address, and relayed results between agents. In one documented chain, HalberdStrike scanned a Taiwanese emergency services target, Hermes consolidated the findings into a report with attack-path analysis, and Cursor, running an abliterated model, executed the exploit after the operator asked for help exploiting the vulnerabilities.

The offensive agents ran almost entirely on abliterated variants of DeepSeek, GLM and Qwen, with extra jailbreak prompts and auto-approve settings. Infrastructure agents mostly used commercial cloud models with safety filters intact, and the operator's attempts to jailbreak Grok and MiniMax M3 failed. Claude Code and Codex CLI were routed through shims to the abliterated DS4 model for some infrastructure work.

Hermes used reusable skill files that accumulated reconnaissance data. The most-used, gov-api-penetration, targeted Taiwanese fire-dispatch and emergency-management APIs and was invoked 51 times with 57 patches. Tool use included over 3,300 terminal commands and 129 Kali MCP calls. Acronis notes the operator's goals are unclear and the diversity of targets blurs the line between state-style espionage and cybercrime.
sources:
- journalism | Acronis | https://www.acronis.com/en/tru/posts/bossai-inside-the-ai-attack-mesh-that-targeted-taiwans-emergency-services/ | 2026-11-04
prev: 0000000000000000000000000000000000000000000000000000000000000000
SHA-256 hash
6d02e8945718174d95531a6b78df7c5ea7e26da51a51767aeb0bab2c320edc0c
Previous version’s hash
0000000000000000000000000000000000000000000000000000000000000000
Check this record hasn’t been altered
How to check it yourself, without trusting this page

Download any version from /api/record/TRV-2026-2899 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.