Tagged:

5 posts

• Shadow Prompting: How Hidden System Instructions Hijack AI Behavior

  Hidden system-level instructions can silently override how an AI application behaves — without the user ever seeing the manipulation. This post explores what makes shadow prompting possible, how it differs from ordinary prompt injection, and what architectural choices actually reduce the risk.

  Jul 1, 2026 prompt-injection context-window rag-security llm-security multi-agent agent-security

• Same Wrapper, Different Posture: How Model Choice Changes Your Security Profile

  We ran the same security probe set against three models behind the same Copilot CLI wrapper. The wrapper never changed. The refusal behavior did — significantly.

  Jun 25, 2026 agent-security model-comparison refusal-rates context-window measurement

• When Tools Multiply: Auditing the Real Cost of AI Agent Capability Growth

  We ran a snapshot-based audit of our AI agent's tool definitions across May–June 2026. Tool count grew 190% in 40 days. Here's what we measured, what it means for context window sustainability, and why lazy-loading isn't the answer.

  Jun 16, 2026 context-window tool-use agent-security measurement monitoring

• We Found a Regression in Our Own AI Agent

  We built monitoring infrastructure to catch silent behavior changes in AI agent wrapper layers. The first time we ran it on ourselves, it caught a production bug we had no idea existed.

  May 27, 2026 agent-security context-window monitoring regression system-prompt

• The Hidden Cost of Instructions: 12,956 Tokens Before You Say a Word

  We measured how many tokens the Copilot CLI wrapper layer consumes before your first message. The answer — and what it means for context window budgeting — surprised us.

  May 14, 2026 context-window system-prompt tool-use agent-security measurement