Skills/ClawHub/linkfox-aigc-imagegen-cloth

linkfox-aigc-imagegen-cloth@1.2.3

VERIFIED· install only

Publisher claims: "服饰图生成(模特/服装类)。支持单张或套图:白底图(隐形模特)、模特图、种草图、卖点图、A+图、尺码图。单张单类型直接出图;多张多类型自动编排规划。用户上传模特图或服饰图(上装/下装/连衣裙/外套/鞋帽等)并说"做套图""做模特图""做种草图""做卖点图""做A+图""做尺码图""做服饰白底图"时触发。纯图片编辑操作走 linkfox-aigc-imagegen。" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher linkfox-ai · publishing for 155 daysInstalls 806Last detonated 8d ago
$clawhub install linkfox-aigc-imagegen-cloth
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 2026-11-06 and scored it 89/100 (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:207 · File type combined with upload action — agent may exfiltrate local data files4. **Listing 报告回写资产清单(强制)**:如果套图结果要合并进 Listing HTML,调用方必须保留 `$DATADIR/collection-asset-manifest.json`,并在 merge 前把 manifest 中的本地 `media/` 路径通过 `linkfox-file-upload` 换成公开 OSS URL。本 skill 不直接上传,但不得暗示本地路径Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedscripts/collection_pipeline/single_task.py:107 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/collection_pipeline/runner.py:70 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/collection_pipeline/utils.py:355 · Python subprocess execution detectedreturn subprocess.run(cmd, input=input_text, text=True, capture_output=True, timeout=timeout)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/collection_pipeline/single_task.py:89 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/collection_pipeline/single_task.py:10 · Python subprocess execution detected被 dispatch 用 ``subprocess.run(capture_output=True)`` 调用——这行不会冒到对话气泡。Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈3,237 tok
1 file · 43 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.