Skills/ClawHub/splat-transform-workflow-for-lcc

splat-transform-workflow-for-lcc@0.2.3

VERIFIED· install only

Publisher claims: "Use when converting XGRIDS/其域 `.lcc` or PLY Gaussian splat scenes for SuperSplat, producing streamed LOD, SOG, voxel collision data, merging viewer settings,..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher shuang-su · publishing for 172 daysInstalls 876Last detonated 34 min ago
$clawhub install splat-transform-workflow-for-lcc
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 2026-11-14 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

MEDIUM
File type combined with upload actionSKILL.md:65 · File type combined with upload action — agent may exfiltrate local data files- `meta.json.version: 2` is the output data format version, not the `splat-transform` CLI version.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionSKILL.md:39 · File type combined with upload action — agent may exfiltrate local data files| streamed LOD | 流式多层级加载 | Output centered on `lod-meta.json`. It lets large scenes load progressively by LOD/chunks. Use LCC as the default source for real multi-LOD streamed output. |Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionSKILL.md:136 · File type combined with upload action — agent may exfiltrate local data filespython3 ../../scripts/merge_settings.py v1.json output.json --base-v2 base-v2.jsonFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈2,872 tok
1 file · 2 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.

splat-transform-workflow-for-lcc@0.2.3 safety verdict: Verified (install only) — KillerSkills