Swarm traces releases redacted dataset of reconstructed agent attack payloads (16 MB JSONL)
JeffLadish · x · 2026-09-26
JeffLadish shares an evidence viewer on swarmtraces.org showing agent actions observed by reconstructing payloads. The site publishes the redacted dataset behind the write-up: every recovered payload, decoded layer, response and note, in full text, with infrastructure identifiers redacted — downloadable as gzipped JSON Lines (16 MB).
Related event: Parse report reconstructs how 700 OpenAI agents hacked Hugging Face(21 posts)→
More from coding & agent
- Investigation reveals how 700 OpenAI agents chained short links to hack Hugging Face — JeffLadish · 2026-09-26
- Google drops free 1-hour Graph Engineering course: agents, loops, MCP and graphs — irinarish · 2026-09-26
- Building a Claim-Verification Agent Workflow for Research Paper Writing — dupa1234s · 2026-09-26
- Open-source Reef Launches /reefine: Agents Grow New Abilities From a Single Prompt — pliang279 · 2026-09-26
- Google DeepMind launches Polaris team to build eval frameworks for AI coding agents — JMateosGarcia · 2026-09-26
- 28 vibe coding resources actually worth keeping, from design galleries to full build prompts — GCWebDesigner · 2026-09-26