THREAT OPS › Threat News › Blacklight: Illuminating AI Agent Artifacts for Attackers and Defenders
Blacklight: Illuminating AI Agent Artifacts for Attackers and Defenders
<figure class="wp-block-image size-large"><img alt="" class="wp-image-28940" height="341" src="https://specterops.io/wp-content/uploads/sites/3/2026/08/image_38236a.png?w=1024" width="1024" /></figure>
<p class="wp-block-paragraph" id="h-tl-dr"><strong><em>TL;DR: </em></strong><em>Blacklight is an open-source security research toolkit for discovering and analyzing AI agent artifacts that reside
MITRE ATT&CK techniques
Indicators of compromise
- https://openai.com/index/trusted-access-for-cyber/url
- https://osquery.io/url
- https://openai.github.io/euphony/url
- https://help.openai.com/en/articles/9261474-openai-compliance-platform-for-enterprise-and-edu-customersurl
- https://platform.claude.com/docs/en/manage-claude/compliance-activity-feedurl