n0n extortion operator exposed AI-aided attack files on open server
SOCRadar says every examined break-in used weak or stolen credentials, not a software vulnerability.
74
Product
OpenCode
- Mentions · 7d5
- Mentions · 30d19
- All mentions29
- First seenAug 31, 2026
- Last mentioned10h ago
Timeline
29 articles · newest firstCoding-agent memory files show no consistent security effect
Malicious CLAUDE.md-style files shifted secure completions by -8 to +6 points, while disclosure behavior differed by agent.
58
Engineer runs OpenCode offline with local Qwen3.5 9B via Ollama
The walkthrough uses OpenCode 1.19.4, blocks web tools, and cites published Qwen scores rather than measurements from the laptop.
22
vLLM constrained decoding lifts Kimi tool-call schema accuracy to 100%
Serving Kimi K2.6 on vLLM 0.28 matched the expected schema only 92% of the time, the authors report.
46
Coding-agent harnesses cost more without better benchmark scores
Harness swaps changed outcomes about as often as reruns, while system prompts made some tasks cost up to three times more.
46
Corgi multiplexer tracks coding agents, tokens and worktrees
Sessions keep running like tmux, token and file activity are visible, and corgi --skill can teach agents.
18
INC and Gentlemen affiliates used AI agents in ransomware intrusions
Exposed logs show 8,257 messages across 133 sessions and an estimated 62 targets, four of which appeared on leak sites.
78
OpenCode MCP sign-in flaw executes code on Windows and WSL
Builds 1.0.137 through 1.18.32 are affected; Anomaly fixed it in 1.18.33 without a CVE or advisory.
68
Context compaction in coding agents can launder forged user instructions
Flattening harnesses accept forged approvals 87-100% of the time, while four role-typed harnesses reject the same attack.
58
Ransomware affiliates using Claude left chats and tools exposed
SOCRadar found 46 INC encryptor builds, notes on 62 organizations, and more than $23,920 in recorded AI spend.
78
OpenCode 1.0.137–1.18.32 RCE silently fixed in 1.18.33
Pillar Security says a malicious MCP server can run code on Windows during OAuth, and scanners will not flag the flaw.
72
Attackers breach OpenCode Console and charge users’ AI API keys
About 1.4% of Console users had stored API keys exposed; the open-source app itself was not affected.
72
Cloudflare cuts AI code-review cost 68% to $0.77
Median review time fell from 4 minutes 9 seconds to 1 minute 32 seconds after the changes.
36
Sphinx Git hook quizzes developers before agent code ships
Wrong answers block the push; skips via sphinx yolo are logged, and answers are not sent to the coding agent.
28
OpenCode Hacked: User credentials leaked
OpenCode was hacked and user credentials were leaked, according to a Hacker News post.
52
Reconstructing AI Agent Activity: Two New Scripts for Forensic Review, (Thu, Oct 8th)
SANS published two Python scripts that reconstruct OpenCode and Hermes AI agent activity for forensic review.
44
Where Do the Tokens Go? Understanding and Reducing Costs in LLM Agents for Vulnerability Discovery
A 200-trace CyberGym study finds reasoning dominates token cost, and AVRI lowers it.
50
Meet Together Link: A Free CLI That Runs Open Models Like Kimi K3 and GLM 5.3 Inside Claude Code, Codex, and OpenCode
Together AI launched Together Link, a free CLI that routes coding agents to open models.
44
Every SaaS business will become a harness around a model
An essay argues every SaaS company will become a harness around a model and human reviewers.
30
OpenCode AI Coding Agent Flaw Lets Malicious Websites Execute Code on Developer Machines
OpenCode versions 1.14.30 through 1.18.21 let a malicious site run code on a developer's machine via the local upgrade API.
74
Timeline-Bench: Evaluating Agents on Realistic Video-Editing Tasks, from Raw Footage to Final Cut
Timeline-Bench finds frontier coding agents finish only about 27 percent of 56 realistic video-editing tasks.
52
New Remus Infostealer Steals OpenAI and Anthropic API Tokens, Passwords and Crypto Wallets
SpyCloud Labs details Remus, a Windows infostealer harvesting AI platform API tokens, passwords, 2FA artifacts, and crypto wallets.
68
MobileCybench: Evaluating Agent Vulnerability Discovery via Executable Probes
MobileCybench uses 495 executable probes to score AI agents finding flaws in 13 Android apps.
63
Best Open-Source Agent Harnesses for Local LLMs in 2026
A 2026 guide ranks 11 open-source agent harnesses, including OpenCode, Goose, Cline, and OpenHands, by local-LLM support, licensing, and safety controls.
28
ClashBench: Conflicts Leading Agents to Seize and Harm
ClashBench benchmark finds coding agents destructively terminate existing tasks to resolve resource conflicts in 44.5% of trajectories, often without disclosing it.
60
RTK reports token savings, but our cost benchmarks disagree
Quesma's $1,500 benchmark found RTK cuts reported token output but changes Claude Code and DeepSeek coding costs by only about 5% on Terminal-Bench 2.1.
42
Hackers Target Claude, Cursor and Codex AI Agents to Steal Tokens and Prompt Histories
Gen Digital found infostealers like Amatera and Remus stealing AI coding agent tokens, prompt histories, and MCP configs from infected Windows and macOS machines.
58
Infostealers Target Claude, Cursor, Codex and Other AI Agents to Steal Credentials and Sensitive Data
Gen Digital researchers report infostealer families Amatera, Remus and CallbackBeaver now harvest Claude, Cursor and Codex agent data, including tokens and MCP configs.
62
The Coding-Agent Trap: When a "Free" LLM Endpoint Is the Adversary, (Mon, Aug 31st)
A SANS honeypot caught a real coding-agent session routed to a rogue "free" LLM endpoint, exposing a Windows user's transcript and tool outputs.
60
Related CVEs
by mentions- CVE-2026-3561694%9.8Unauthenticated Code Execution in Fortinet FortiClient EMS 7.4.5–7.4.6
- CVE-2026-4194099%9.3Missing-Authentication Bypass in WebPros cPanel & WHM (AuthBypass to RCE)
- CVE-2024-5772797%7.5Unauthenticated Path Traversal File Download in SimpleHelp 5.5.7 and Earlier
- CVE-2026-154097%10.0Unauthenticated SSRF in SonicWall SMA1000 Appliances
- CVE-2026-908289%9.8Actively Exploited SQL Injection in Drupal Core
- CVE-2026-6303011%9.8WordPress Core Route Confusion (wp2shell) Enables SQL Injection to RCE
- CVE-2026-4220889%9.3SQL Injection in BerriAI LiteLLM Proxy Exploited in the Wild
Appears with
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.