Color me curmudgeon, but automated dependency updates should never be a consideration.
Also, one thing I do like that Github does is that it can be configured to send you a report of dependency changes (in yarn, for example).
Color me curmudgeon, but automated dependency updates should never be a consideration.
Also, one thing I do like that Github does is that it can be configured to send you a report of dependency changes (in yarn, for example).
Pinned (major.minor.patch) versions and ignore-scripts should be the default. It's insane that the default is to execute untrusted code from the Internet.
It reminds me of back when IE would let me download a bat file and execute it
/Getoffmylawn
“cooldown” is exactly what it sounds like: a window of time between when a dependency is published and when it’s considered suitable for use. The dependency is public during this window, meaning that “supply chain security” vendors can work their magic while the rest of us wait any problems out.
pnpm has minimumReleaseAge https://pnpm.io/settings#minimumreleaseage
Been using renovate a while, 42 added this as a default!
minimumReleaseAge: 3 dayswill now be set by default for npm inconfig:best-practices
Most of the supply chain vulnerabilities I've seen published and talked about lately have been trying to do things like exfiltrate keys/secrets from developers, including ci.
So of you've got a pr open with the vulnerable package update on it then you've goofed. Even potentially without merging if you've not got ci set up very securely, which is probably more common than we'd like to admit
No no no, I should be using dependency cooldowns. You all should be finding the vulnerabilities and getting them fixed before they reach me.
I don't get your point. In most examples cited in the article, the supply chain attacks were found either by security researchers or maintainers realizing they did not intentionally push compromised version, not by everyday developers. The goal of dependency cooldowns is to give researchers and maintainers more time to detect attacks before they reach end-users.
If we all use them, won't attackers switch to waiting an extra week before attempting to activate their attacks? This feels similar to antibiotics resistance in bacteria coming from over use of antibiotics.
all 9 comments