Sentry founder on agent permissions: no secret read access by default
zeeg · x · 2026-11-17
Sentry founder David Cramer weighs in on what permissions AI agents should get: he'd deny any read access to secrets by default, and allow write access only case by case. His mental model: "If Joe accessed my computer, what could he do?" — and an agent adds prompt injection risk on top of Joe.
He argues it depends on the state of the world: exfiltration opportunities are too easy today, so nothing is safe by default. Vendors have a responsibility to protect users who won't make the right decisions but will blame them afterwards — Sentry's approach is to only expose safe credentials like DSNs and SENTRY-prefixed variables.
More from coding & agent
- Sentry CEO on MCP credential exposure: only safe tokens, no general secrets management — zeeg · 2026-11-17
- Developer forces AI agents into early live testing, surfacing 7 real Windows sandbox bugs — kevinkern · 2026-11-17
- llm-blocks: Swap MLA, Mamba-2, MoE blocks in your LLM with one line of code — cneuralnetwork · 2026-11-17
- Profound CTO dbabbs: software engineering isn't cooked — CS will matter most in the AI era — soleio · 2026-11-17
- Fable 5.2 just wants a goal, then to work alone for hours without you — victormustar · 2026-11-17
- LangChain raises $300M Series C at $3B valuation, launches LangSmith Agent Platform — LangChain · 2026-11-17