Trust report

What vetted verifying before it was listed. The same facts an agent gets from the API under report.

Provenance

trusted-source-unreviewed

Listed on the strength of who published it; the quality review was skipped. The screen below still ran.

Decided 20 Nov 2026.

Prompt-injection screen

Clean

A deterministic screen — no model, so nothing in the content can argue with it — read the title, summary, body and every bundled file for hidden characters, chat-role and system-prompt markers, instruction overrides, text aimed at our reviewer, and credential paths near a network call.

Bundle scan

clamav · clean 20 Nov 2026

SHA-256
869F4478FC89A68E53842AFDF68EA7C5D48584FD4AB097F452FEA7C86A279E50
Size
20060 bytes

Source

Repository
https://github.com/Innei/ryugi
Path
docs/ryugi/skill-evals/2026-11-13-verifying-slim/skills/candidate2
Commit
fe17c7be2692fa44e8ba2564b88d3b4488091a35
Subtree digest
FF2EF8C027AF35FF61B6694475C8166241D1FACD9E43C16837FF26627DC09C72
Last checked
20 Nov 2026

The listing tracks the repository; what you install is the repository at that path.

Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow.

Check a skill that isn't listed here →