Threadlinqs IntelligenceStart free

Threat video1:00

OpenAI API Reasoning Leak via Compaction: Detection & IOCs

OpenAI's compaction endpoint returned encrypted GPT-5.6 reasoning as readable text: 9 detection rules, 9 IOCs and a free Splunk SPL rule.

Read the full threat intel for OpenAI API Reasoning Leak via Compaction: Detection & IOCs →

Chapters

  1. 0:00The hookCompaction smuggling extracts about 609 tokens.
  2. 0:04The storyPrior attacks were mitigated in August.
  3. 0:11Attack pathThey harvest encrypted reasoning from gpt-5.6.
  4. 0:27AttributionNo threat actor: this was defensive research.
  5. 0:32Indicators of compromise5 indicators to hunt: 2 domains, 2 URLs and 1 file name.
  6. 0:38MITRE ATT&CK techniques3 ATT&CK techniques, from initial access to collection.
  7. 0:43Remediation3 steps now: No developer action required.
  8. 0:50Detection rules9 detection rules, in SPL, KQL and Sigma.
Transcript

0:00Compaction smuggling extracts about 609 tokens.

0:05Prior attacks were mitigated in August.

0:07Researchers found a bypass in October.

0:11They harvest encrypted reasoning from gpt-5.6.

0:15Researchers reproduced compaction with preserved reasoning.

0:19Swap spaces for tabs, evade filters.

0:22Weaker models echo the plaintext back.

0:27No threat actor: this was defensive research.

0:325 indicators to hunt: 2 domains, 2 URLs and 1 file name.

0:383 ATT&CK techniques, from initial access to collection.

0:433 steps now: No developer action required.

0:519 detection rules, in SPL, KQL and Sigma.

0:56Threadlinqs. The unified security engineering platform.