trading-coach

SAFE max severity MEDIUMSkillSpector Caution 0 registry clawhub.ai last scanned 2026-02-07 1 scan

Verdict safe, but 3 findings (3 medium), mainly data exfiltration. Most recent scan 2026-02-07.

This trading analysis skill presents MEDIUM security risks primarily related to supply chain security and sensitive data handling. The skill requires users to clone an external GitHub repository and install unpinned dependencies without verification mechanisms, creating supply chain vulnerabilities. Additionally, it processes highly sensitive financial trading data (broker CSV exports containing transaction history and P&L information) without providing security guidance on data privacy and handling. The skill itself does not contain malicious code in the provided materials - no scripts were included for analysis, only documentation. However, the installation process and data handling practices need security improvements. The missing optional metadata fields (license, compatibility, allowed-tools) reduce transparency but are low severity issues. Overall, this appears to be a legitimate trading analysis tool with supply chain and data privacy concerns that should be addressed.
Scanner's overall assessment (LLM analyzer)

Findings3

Critical0

High0

Medium3

Low0

Analyzersstatic llm meta

Second scanner: NVIDIA SkillSpector

VerdictCaution 0

Score0 / 100

Issues0

Version2.12.0 (static)

SkillSpector found no issues but could not fully inspect the package, usually because SKILL.md refers to a file that is not present, so it fails closed to CAUTION instead of SAFE. Read it as "not fully checked", not as a finding. How the two scanners compare across the whole corpus: Two scanners, one corpus.

What this skill does

🏆 AI交易复盘教练 — 把你的券商CSV变成可执行的改进洞察！自动FIFO配对持仓，8维度质量评分(入场/出场/趋势/风险...)，10维度AI洞察。支持富途(中/英)、老虎、中信、华泰等主流券商。触发条件: 用户提供交易CSV、要求分析交易表现、评估交易质量、生成复盘报告、计算盈亏统计、识别交易模式问题、"帮我复盘"、"分析我的交易"。

Package: 4 files, 17 KB
SKILL.md: 271 words, 10 sections
Code: None. Instructions only.

SKILL.md covers: 🏆 Trading Coach — AI交易复盘教练 · ✨ 核心能力 · 🚀 快速开始 · 首次安装 · 一键复盘 · 📈 支持券商 · 🎯 评分体系 · 💡 AI洞察 · 📊 输出示例 · ☕ 支持作者

Findings

MEDIUM Hardcoded External Repository Clone Without Verification Data Exfiltrationllm

The installation instructions direct users to clone a GitHub repository (https://github.com/BENZEMA216/tradingcoach.git) without any integrity verification, version pinning, or provenance checking. This creates a supply chain risk where malicious code could be introduced through repository compromise or typosquatting.

SKILL.md

git clone https://github.com/BENZEMA216/tradingcoach.git ~/tradingcoach

Remediation: Add commit hash verification, use signed releases, or include integrity checksums. Document the expected repository state and warn users to verify the source.

MEDIUM Unpinned Dependency Installation Data Exfiltrationllm

The skill instructs users to run 'pip install -r requirements.txt' without specifying or documenting pinned versions. This creates supply chain vulnerability where malicious or compromised package versions could be installed.

SKILL.md

pip install -r requirements.txt

Remediation: Pin all dependencies to specific versions in requirements.txt. Use hash verification (pip install --require-hashes). Document expected package versions.

MEDIUM Sensitive Financial Data Processing Without Security Guidance Data Exfiltrationllm

The skill processes sensitive financial trading data (CSV files containing transaction history, account positions, P&L data) but provides no security guidance on data handling, storage, or privacy. Users may inadvertently expose sensitive financial information.

SKILL.md

将券商导出的CSV交易记录,转化为专业级复盘报告 - processes broker CSV exports containing sensitive trading data

Remediation: Add explicit security warnings about: (1) Not sharing CSV files containing real trading data, (2) Data retention policies, (3) Secure deletion after analysis, (4) Privacy considerations when using AI analysis features.

What is in the package

File	Kind	Size
`SKILL.md`	doc	3.6 KB
`references/csv_formats.md`	doc	3.6 KB
`references/insight_dimensions.md`	doc	5.2 KB
`references/scoring_system.md`	doc	5.1 KB

External hosts referenced

github.com buymeacoffee.com

Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.

Environment variables referenced

BROKER_CONFIGS

Package contents recorded 2026-10-22. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.

What we checked

Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
Meta analyzer. A second model pass that validates, deduplicates and re-scores the other analyzers' findings.

What we did not check

Runtime behaviour. The skill was not executed; findings come from reading its files.
Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
Content the analyzers cannot read: images, binaries, and some non-English text.
Known scanner bypass classes. See the methodology and limitations page.

Sources

Repository: https://clawhub.ai/skills/trading-coach
Raw scan result: trading-coach-scan.json
Badge for your README: ![skillscan.io](https://skillscan.io/badge/clawhub-ai-trading-coach.svg)
Request a re-scan

Second scanner: NVIDIA SkillSpector

What this skill does

Findings

What is in the package

External hosts referenced

Environment variables referenced

What we checked

What we did not check

Sources

Related skills