Skills/ClawHub/financial-engineer-digital-employee

financial-engineer-digital-employee@2.0.6

VERIFIED· install only

Publisher claims: "覆盖数据探查、单变量分析、特征工程、LR评分卡、XGBoost/DNN建模、超参数调优、模型解释、多模型对比、分群建模、DeepModel集成全流程。从数据到模型上线的一站式机器学习建模能力。" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher gechengling · publishing for 181 daysInstalls 1,295Last detonated 29 min ago
$clawhub install financial-engineer-digital-employee
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

What changed since 2.0.5

vet-skills diff financial-engineer-digital-employee 2.0.5 2.0.6

In the sandbox, this version reached for nothing 2.0.5 did not. Compared from the two recorded runs, not from source.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

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 2026-11-16 and scored it 92/100 (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:2788 · File type combined with upload action — agent may exfiltrate local data files--config ./config.json --output_dir ./outputs/deepmodelFix: 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:2070 · File type combined with upload action — agent may exfiltrate local data files2. **各模型文件**:XGB(.json) / LR(.joblib) / DNN(.pt,含 imputer+scaler 元数据)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:2780 · File type combined with upload action — agent may exfiltrate local data files"submodel_paths": ["./outputs/deepmodel/高风险.json", "./outputs/deepmodel/低风险.json"],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:2737 · File type combined with upload action — agent may exfiltrate local data files--auto --config ./config.json --output_dir ./outputs/deepmodelFix: 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:2834 · File type combined with upload action — agent may exfiltrate local data files"submodel_paths": ["./outputs/deepmodel/高风险.json", "./outputs/deepmodel/低风险.json"],Fix: 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
≈17,965 tok
1 file · 1 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.