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
- Mentions · 7d0
- Mentions · 30d1
- All mentions6
- First seenSep 9, 2026
- Last mentioned9d ago
Timeline
6 articles · newest first[AINews] Opus 5.5 is good at explainer videos
Claude Opus 5.5 leads SimpleBench at 88.4% as GPT-6, Gemini 3.8 Flash, and MiMo-V2.6-Pro also ship.
80
[AINews] Here are 6 Clones of Jev in 2 days
Jev's non-generative decision model launch drew 36M views and six open clones in two days, positioning discriminative models as fast complements to LLMs.
50
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
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
Appears with
- opencodeproduct · 4
- Claude Codeproduct · 3
- Codexproduct · 3
- Continueproduct · 3
- Cursorproduct · 2
- piproduct · 2
- STG Stealermalware · 2
- Amateramalware · 2
- HydraStealermalware · 2
- OpenHandsproduct · 2
- Claudeproduct · 2
- BeeStealermalware · 2
- Remusmalware · 2
- Aiderproduct · 2
- APEX Stealermalware · 2
- Djinn Stealermalware · 2
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.