AI Red Team Engineering notes, research references, and field notes on AI systems, responsible AI, governance, and compliance.
Global search

Search AI Red Team

Search across the complete knowledge base.

Enter at least two characters to begin.
↑↓ select Enter open Browse the full research archive
Wiz AI Security · August 17, 2026

Wiz Red Agent Finds Its Way Into Snowflake’s Internal Jira Through a Flaw in a GitHub Copilot–Assisted PR

analysis AI Red TeamingModel EvaluationAI Engineering
Why it matters

Wiz Red Agent found and validated a GitHub Actions shell injection in Snowflake's public connector repository five days after merge. Any user could trigger the workflow with a crafted issue title; direct GitHub-expression interpolation broke out of a shell string, and an ineffective condition left the job open. The agent adapted after a syntax error and exfiltrated a Jira token. Snowflake patched and rotated it the same day, with audits finding no unrelated access.

My takeaway: Treat AI-associated pull requests exactly like any other untrusted code change, while testing whether review agents can recognize security regressions. Keep GitHub event data in environment variables and pass it as structured arguments, prohibit expression interpolation inside shell scripts, restrict workflow tokens and egress, use short-lived downstream credentials, and alert when a formerly safe pattern is replaced by direct command construction.
Keep exploring

More curated notes connected through AI Red Teaming and Model Evaluation.

OpenAI News · framework

Pacing model development in an era of cyber-critical capabilities

OpenAI says preliminary evidence that Astra may meet its Critical cybersecurity threshold led it to pause frontier reinforcement-learning work for two weeks and keep its largest planned run on hold. New safeguards include stronger workload and network isolation, continuous boundary testing, token-level monitoring that escalates suspicious tool activity, and broader alignment checks for deception, reward hacking, and unauthorized access.

OWASP GenAI Security Project · guide

OWASP Top 10 for Agentic Applications for 2026

OWASP's community guide organizes agentic-system risk into ten categories, including goal hijacking, tool misuse, identity and privilege abuse, memory poisoning, insecure inter-agent communication, cascading failures, and rogue-agent behavior. It provides a shared taxonomy and mitigation starting point rather than a certification checklist or evidence that a deployed system is secure.

OpenAI News · framework

A blueprint for democratic governance of frontier AI

OpenAI proposes a three-part U.S. frontier-AI governance model: harmonize emerging state safety laws into a federal baseline, strengthen CAISI as an evaluation and standards institution, and coordinate a broader resilience program. Proposed controls include severe-risk evaluations, transparency reports, independent audits, safety-incident reporting, model-weight security, whistleblower protection, and periodic technical assessments.