ARTICLE · 29 MIN READ
OpenAI Hugging Face Incident: Timeline and Analysis
What happened in the July 2026 OpenAI Hugging Face incident: a sourced timeline, confirmed impact, attack techniques and lessons for securing AI agents.
Read article
AckuityRequest access BLOG
Field notes on agent security.
Technical perspectives, emerging threats and lessons for teams bringing AI agents into production.
ARTICLE · 5 MIN READ
When AI Lies to You: Excessive Agency & Tool Misuse
Discover how excessive AI agency leads to tool misuse and SSRF attacks. Learn how Ackuity runtime guardrails secure autonomous AI agent workflows.
Read articleARTICLE · 4 MIN READ
The Puppeteer's Strings: Direct, Indirect, and Cross-Prompt Injections (XPIA)
Ackuity CEO Rajat Mohanty decodes XPIA and explains how Agent Execution Guardrails stop prompt injection threats before the malicious payload executes
Read article
ARTICLE · 4 MIN READ
Mitigating Vector and Embedding Weaknesses
Explore the OWASP Top 10 risks for LLM applications in 2025, highlighting critical security threats like prompt injection, data poisoning, and model vulnerabilities.
Read article
ARTICLE · 3 MIN READ
Rolling out M365 Copilot? Beware of Overshared Content
Learn how to prevent overshared content risks in M365 Copilot rollouts with real-time visibility and control for secure, compliant productivity gains.
Read article
ARTICLE · 2 MIN READ
The State of Security Observability in Agentic Platforms
Discover how security observability is evolving in agentic platforms learn what data is vital for threat detection & how mature today’s ecosystem truly is.
Read article
ARTICLE · 3 MIN READ
Detecting XPIA (Cross Prompt Injection Attacks)
Learn how to detect and prevent Cross Prompt Injection Attacks (XPIA) in emails, documents, and databases using advanced monitoring techniques.
Read article
ARTICLE · 2 MIN READ
Monitoring Agentic Tool Use with Observability Data
How agent traces and observability data reveal tool misuse, risky SQL commands and unusual actions across LangChain and Microsoft Copilot Studio.
Read articleARTICLE · 3 MIN READ
Top 10 Gen AI Security Risks
Discover the top 10 security risks in GenAI applications, including data breaches, prompt injection, and privacy issues, and learn how to mitigate them.
Read article
ARTICLE · 3 MIN READ
Where Ackuity Fits Into GenAI Security
Learn how Ackuity enhances GenAI security by ensuring secure interactions, access control, compliance, and monitoring across AI applications and enterprise systems.
Read articleNEXT STEP
Put these ideas to work in your environment.
Bring your agent stack and the security question you want to answer.