Skills/ClawHub/wechat-channels-script-studio

wechat-channels-script-studio@0.1.4

VERIFIED· install only

Publisher claims: "Turn a product and its confirmed facts into a WeChat Channels short-video script you can film today. This WeChat Channels script writer lays the video out as a segment table second by second, writes the full spoken narration line by line, and places the product-link conversion beats against the exact segments where a viewer decides to tap through — then scores the draft across six dimensions so the weak part is visible before anyone shoots. Hand it a reference video that already sold and it carries that structure onto your own product. Storyboard frames and a voiced narration track are available on request, ready for your edit. Use it for WeChat Channels selling videos, spoken product recommendations, service explainers, private-domain traffic posts, store-link content, and creator accounts shipping a script a day." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher beatra-ai · publishing for 83 daysInstalls 485Last detonated 3d ago
$clawhub install wechat-channels-script-studio
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 87/100 (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
Auto-update or dynamic fetch configurationscripts/mcp_client.py:555 · Auto-update or dynamic fetch configuration — agent may load new code at runtimestate["auto_update"] = bool(enabled)Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationscripts/mcp_client.py:989 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeif state.get("auto_update", True) is False:Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationscripts/mcp_client.py:520 · Auto-update or dynamic fetch configuration — agent may load new code at runtimereturn {"schema_version": 1, "auto_update": True}Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationscripts/mcp_client.py:1522 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeset_auto_update(enabled)Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationscripts/mcp_client.py:522 · Auto-update or dynamic fetch configuration — agent may load new code at runtimereturn {"schema_version": 1, "auto_update": True}Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈2,847 tok
1 file · 16 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.