News for hackers. Stuff that matters.
Re:Cloudflare/Security-Audit-Skill by 9el on Thursday September 17, 2026 @05:20AM (#49738270)
Any clues why "an OS-enforced sandbox" is in requirements?
Re:Cloudflare/Security-Audit-Skill by nicce on Thursday September 17, 2026 @06:29AM (#49738749)
Probably to save their skin if agent starts to do some unexpected things and bringing havoc. But I doubt that OpenAI models with normal subscription, for example, wont even work with this skill.
Re:Cloudflare/Security-Audit-Skill by donk8r on Thursday September 17, 2026 @01:05PM (#49743615)
Runs target builds, tests, fuzzers. No sandbox: workflow won't execute them. Lead stays needs_validation.