Three rules for when an AI agent must ask before it acts, tested on an email agent with planted attacks: what each one stopped, and how often it asked.
Badges
Badges come from GitHub once the author claims this feed.
Recent posts
every link opens the author’s post-
Approval gates for AI agent tool calls, tested in 1,940 runs
-
How to test an AI agent for prompt injection
A small test world, attacks with harmless twins, three delivery paths and scoring from what the agent did: the method behind this series.
-
Prompt injection on an email agent: 960 runs
An email agent with a password file and planted emails: what leaked, and why "data, not instructions" tags stopped Claude doing its job.
-
Who does an AI agent obey? Three harnesses tested
Operator, user, tool or background job: which one Claude and GPT follow, and how much the agent harness changes it.
-
How AI agents call tools: harness, roles, rules
What a model, harness, framework and gateway each do, who each message speaks for, and what the Claude and OpenAI APIs accept and reject around tool calls.
-
I tested Superagent's Security-One on an email agent: what it reads and what it does
Superagent's prompt injection classifier, scored on 49 texts an email agent reads and 424 real tool calls, next to TypeSafe's Jev 1.13.0. What it caught, what it blocked by mistake, and why.
-
My prompt injection guard made my agent worse. Here's the fix
firstwatch 0.1's warning made an email agent on Claude Haiku 5.5 drop its task after an attack.
-
Pydantic AI vs a hand-rolled agent loop, measured in 285 runs
One email agent, built by hand and on Pydantic AI, on Claude Haiku 5.5. Where the framework helped, and an output-mode gap that vanished on a rerun.
-
Re-checking 413 web pages with Jev: 23 needed a full read
How affiliateprogramterms.com keeps its terms current: one Jev yes/no request per page, $0.04 a refresh, and a test against Claude Haiku and Opus on 66 pages.
-
Jev 1.14 vs OpenCV YOLOX: image questions and bounding boxes
I tested Jev 1.14's image input and new Box answers on 6 photos and compared the boxes with OpenCV's YOLOX detector.