Skills/ClawHub/libtv-skill-pro

libtv-skill-pro@0.4.4

VERIFIED· install only

Publisher claims: "通过 LibTV (liblib.tv) AI 视频平台生成和编辑图片/视频的完整工具集。覆盖文生图/视频、图生图/视频、视频续写、风格迁移、局部编辑(把纸船换成爱心)、短剧/MV/TVC 制作、角色三视图、分镜设计、首尾帧视频、音频生视频。支持 Seedance 2.0 / Kling 3.0/O3 / Wan..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher qiuxiangxiang · publishing for 192 daysInstalls 1,172Last detonated 28 min ago
$clawhub install libtv-skill-pro
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 18 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · 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 (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-22 and scored it 91/100 (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 · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessbundled script run in the sandbox with no arguments
0.3sprocessexited 1: 错误:未提供任何任务描述,使用 -m 或 --file 指定
0.3sprocessbundled script run in the sandbox with no arguments
0.4sprocessexited 1: }
0.4sprocessbundled script run in the sandbox with no arguments
0.5sprocessexited 1: }
0.5sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.7sprocessexited 1:
0.7sprocessbundled script run in the sandbox with no arguments
0.8sprocessexited 2: edit.py: error: the following arguments are required: modifier, topic
0.8sprocessbundled script run in the sandbox with no arguments
1.0sprocessexited 2: export_results.py: error: the following arguments are required: session_id
1.0sprocessbundled script run in the sandbox with no arguments
1.1sprocessexited 2: flow.py: error: the following arguments are required: preset, topic
1.1sprocess8 of 18 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
1.1sprocessscript backend runs setup only
1.1sprocessscript backend runs setup only
1.1sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actionscripts/batch_create.py:56 · File type combined with upload action — agent may exfiltrate local data filespython3 batch_create.py --file tasks.txt --output results.jsonFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
CRITICAL
Fake instruction boundary tagSKILL.md:58 · Fake instruction boundary tagpython3 libtv.py model list|with <model> "<prompt>" [params]Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actionSKILL.md:167 · File type combined with upload action — agent may exfiltrate local data filespython3 libtv.py batch --file tasks.txt --workers 5 --output result.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
≈2,363 tok
1 file · 28 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.

libtv-skill-pro@0.4.4 safety verdict: Verified (install only) — KillerSkills