Two AI coding tool incidents this month:• OpenCode: a breach exposed stored provider API keys.• Warp: attackers got in via a vendor and reached some agent trace and telemetry data. Warp hasn't said whether traces held secrets.Lesson: anything pasted into an agent chat can end up in a log you don't control. Keep keys in env files or a secrets manager, and rotate any you've pasted.#infosec #AppSec #AI #vibecoding #devtools #cybersecurity #security #webdev #indiehackers
Related
Otter.ai is adding 27 languages, its biggest expansion yet, for 31 in total. A new multilingual transcription feature wi...
Otter.ai is adding 27 languages, its biggest expansion yet, for 31 in total. A new multilingual transcription feature will follow meetings as speakers switch languages, with no set...
Tool calling lets AI do more than chat—it executes actions! LLMs request functions, your app executes them, results feed...
Tool calling lets AI do more than chat—it executes actions! LLMs request functions, your app executes them, results feed back to the model. Dive into a practical .NET example. #AI ...
Pour fiabiliser vos agents de code, soignez ce qui les entoure plutôt que vos prompts : docs lisibles par l'agent, conte...
Pour fiabiliser vos agents de code, soignez ce qui les entoure plutôt que vos prompts : docs lisibles par l'agent, contexte chargé à la demande, validation rapide.Un article tiré d...