Cloudflare/Security-Audit-Skill

hyperionultra | a day ago

Uf, how much tokens?

jesse_dot_id | a day ago

At least 150k on my relatively small FastAPI project, but hit my session limit. Continuing in a few hours.

chrisweekly | 20 hours ago

Oof. YAGNI. 150k tokens is where you start hitting the "dumb zone" (model attention issues and inconsistent adherence to instructions).

drchaim | a day ago

I threw 1M tokens for nothing in a medium codebase.

TZubiri | a day ago

how much is medium codebase, like 50kloc including docs?

throwup238 | a day ago

500kloc plus at least ten million lines of gastown logs.

For a todo cli. That doesn’t work.

this_user | 23 hours ago

Welcome to agentic coding in 2026.

drchaim | 23 hours ago

in this case medium is relative to the projects I've worked. Bad expression anyway.

SkyPuncher | 17 hours ago

These work best on a targeted section of the code, like a PR.

prodigycorp | a day ago

Hi Cloudflare people, if you are reading this. Please clean up your Cloudflare. Skills. There are way too many skills for the platform. You should consolidate all of your skills into a single skill and route everything thru that skill. The way it is right now pollutes our context window.

https://github.com/cloudflare/skills/tree/main/skills

m00dy | a day ago

I'm sure they read here.

dewey | 23 hours ago

They actually do.

m00dy | 18 hours ago

yeah I know :D

bravetraveler | 22 hours ago

John Cloudflare: https://news.ycombinator.com/user?id=eastdakota

kentonv | 18 hours ago

We actually do.

I forwarded this to the right person, and it sounds like it's being worked on. Thanks!

tomrod | 18 hours ago

Once again, proving my growing trust in Cloudflare is well placed. Thanks!

prodigycorp | 4 hours ago

I complain because I like using CF. Thank you.

acoyfellow | 18 hours ago

we do <3

mooktakim | 22 hours ago

I really don't understand why they didn't create an "app store" style skills library where it could be approved and scanned for security issues

simlevesque | 20 hours ago

14 skills with short descriptions doesn't seem like an issue to me.

prodigycorp | 18 hours ago

The descriptions are shorter now, but they used to read like ads. The skill split still feels arbitrary. You turn on what you think you need, then hit some Cloudflare task that needs another skill and have to go fetch it.

I don’t get why these need to be separate. One skill with progressive disclosure already handles this. That’s kind of the point.

riffic | 16 hours ago

a skill issue.

9el | 23 hours ago

Any clues why "an OS-enforced sandbox" is in requirements?

nicce | 22 hours ago

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.

[OP] donk8r | 16 hours ago

Runs target builds, tests, fuzzers. No sandbox: workflow won't execute them. Lead stays needs_validation.

gbrindisi | 23 hours ago

Shameless plug: in case someone finds this requiring too many tokens, we shared the recipe on how we built our own in house audit skill so that it can easily be replicated and tuned to different environments https://www.synthesia.io/post/automating-code-security-revie...

gyanchawdhary | 22 hours ago

This is awesome. Thanks for sharing

wslh | 20 hours ago

Tip for security professionals using LLMs: audit skills that explicitly frame the task as security research sometimes trigger refusals from the top OpenAI and Anthropic models because they guard against misuse. What works for me: separate skills for bug classes (and bugs in general) without the security framing, plus another skill that combines their findings to spot security bugs.

viraptor | 19 hours ago

If you're a security professional, go through their validation. You won't get the security refusals anymore. Well... you'll still get the occasional downgrade from Fable, but not the "oh no, I can't do exploits for you" breaks.

xur17 | 18 hours ago

Except their validation doesn't seem to work. I've gone through both (both personally and for my company), and.. no response for weeks.

tonymet | 18 hours ago

What’s the difference between a skill and a prompt? Separate files? Aren’t tokens, tokens?

fassssst | 17 hours ago

Skills can have scripts packaged with them

acedTrex | 17 hours ago

Incredible, a post and repo dedicated to a markdown file, the downfall of this field has been swift.

vntok | 17 hours ago

Did you open the repo? There's a subdirectory with two dozens of files, around 300Kb of text.

Storing/visualizing small text changes over time as revisions is exactly what Git is excellent at, how else would you keep track of updates to the prompts?

acedTrex | 17 hours ago

> how else would you keep track of updates to the prompts

I dont? because prompts are not a thing that are ever needed to be tracked lol.

decidu0us9034 | 15 hours ago

but they're very huge markdown files. look how much junk they're polluting the conext window with.

qsbuilder | 16 hours ago

Dumping 14 full schemas into the prompt is just lazy design. You burn tokens, spike latency for no reason