Cloudflare shipped the security review as a skill. its security-audit-skill, the top trending repo…
cloudflare shipped the security review as a skill. its security-audit-skill, the top trending repo september 19, runs multi-phase audits and emits machine-readable findings a human can verify, so the agent's claims stop being a black box.
audits became reproducible.
Context
Cloudflare's security-audit-skill repository describes a coding-agent skill for multi-phase security audits with independently verified, machine-readable findings. It was created on 18 June 2026, uses an MIT license, and showed 2,665 stars when fetched on 4 October 2026. Its phases are recon, hunt, validate (separate agents try to disprove each finding), report (REPORT.md), structured output (findings.json checked against a schema), and independent verification by fresh agents, and repeated runs are additive.
The multi-phase design and machine-readable output are first-party. The repo was created in June, and no release or announcement dated 19 September was found, so shipped at the note's date is not established. Top trending on 19 September was not found on a trending page. The repo says findings are verified by independent agents, and verification by a human is the note's reading. It also says runs explore different code paths and add to each other, which points away from identical repeat output, so audits became reproducible is the author's take.
Related work
- Earlier note on the Cloudflare audit skill ↗Same repository, different thesis.
- Earlier note on the trending security skill ↗Same repository and trending claim.
Watch next
- A Cloudflare blog or release for the skill and independent false-positive rates.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 21 September 2026 at 13:53 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →