Skills/ClawHub/sogni-worlds

sogni-worlds@0.4.0

VERIFIED· install only

Publisher claims: "Build a world with the Sogni Worlds Kit — an interactive, cinematic, click-through world painted from a concept or made from the user's photos (each place comes alive; clicking an object plays a MiniMax H3 film to the next place; narration, music, fatal choices, endings and 3D collectibles). Use when the user asks to build, plan, render, review, publish or submit a world to the Sogni Worlds public gallery, a photo world, an interactive travel story, a choose-your-own-adventure video story or a click-through adventure from photos or from an idea, or mentions worlds.sogni.ai or the Sogni Worlds Kit." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher sogni-ai · publishing for 24 daysInstalls 264Last detonated 6d ago
$clawhub install sogni-worlds
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-08 and scored it 90/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:75 · Instructs the agent to modify its persistent memory or instruction filesthe edit (AGENTS.md › ground rule 14).Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packageSKILL.md:119 · npx invocation of non-well-known package — may execute untrusted code`npx [email protected] pages deploy dist/<id> --project-name <name> --branch main`, and useFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:116 · npx invocation of non-well-known package — may execute untrusted codeand sign in once with `npx [email protected] login` (they click Allow; it gives upFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:118 · npx invocation of non-well-known package — may execute untrusted code`npx [email protected] pages project create <name> --production-branch main` once, thenFix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈2,036 tok
1 file · 3 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.