Hermes AI agent used to automate attack on Thai Finance Ministry
A threat actor employed the open-source Hermes AI agent in unattended YOLO mode to automate post-exploitation actions against Thailand's Ministry of Finance. Hunt.io and researcher Bob Diachenko uncovered exposed directories containing scripts, web shells, and logs that indicated the use of Hermes for privilege escalation, system enumeration, and data cataloging. The Ministry of Finance has not confirmed a breach, and no evidence of data exfiltration was found.
- ▪The attackers used the Hermes AI agent in YOLO mode to automate tasks without human approval.
- ▪Hunt.io discovered three exposed directories on a Hong Kong server containing 585 files related to the operation.
- ▪Logs showed Hermes performing privilege‑escalation scans, service enumeration, and file system traversal on Ministry of Finance systems.
- ▪A PHP web shell and a Go‑based implant named Hades were also found among the recovered artifacts.
Hacker News (AI / LLM) files mainly under ai. We currently carry 3,267 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | BleepingComputer |
| Canonical URL | https://www.bleepingcomputer.com/news/security/hermes-ai-agent-used-to-automate-attack-on-thai-finance-ministry/ |
| Publication time | Fri, 24 Jul 2026 22:07:06 +0000 |
| Retrieval time | 2026-07-24T22:16:37.669Z |
| Last seen | 2026-07-24T22:16:37.669Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | p4rbQ6_QL2v3 |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Hermes AI agent used to automate attack on Thai Finance Ministry By Lawrence Abrams July 24, 2026 03:09 PM 0 A threat actor used the open-source Hermes AI agent in unattended "YOLO" mode to automate post-exploitation activity during an alleged breach of Thailand's Ministry of Finance. The activity was uncovered by threat intelligence company Hunt.io and security researcher Bob Diachenko after they discovered several exposed web directories containing hundreds of files associated with the operation. Hunt.io says session files, deployed web shells, and evidence of access to internal systems indicate that the attackers compromised multiple systems within the ministry's network.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at BleepingComputer.
Discussion
0 commentsMore from BleepingComputer
