Concrete Stock Daily Reporter

• Outcome: Review
• Latest audit: May 29, 2026 · 9:39 PM UTC
• Version: 1.0.0

Overview

This stock-reporting skill mostly matches its purpose, but it can send a user's report to a hard-coded Feishu recipient and includes optional persistent scheduling.

Review before installing. Replace or remove the hard-coded Feishu target in send_report.sh, confirm the exact recipient before any send, and do not enable the cron entry until the stock arguments and recipient are correct. Treat generated reports as potentially sensitive investment-interest data, and consider fixing the scripts to use verified HTTPS for market data.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Rogue Agent: Self-Modification, Session Persistence
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection

Findings (9)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 88% confidence
• Finding: The skill explicitly requires outbound network access to third-party market-data services, yet no permissions are declared. This creates an authorization and transparency gap: operators and users cannot accurately assess or constrain what external communication the skill performs, which is risky in an agent setting.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 94% confidence
• Finding: The skill description understates several impactful behaviors: contacting external finance APIs, sending messages to Feishu, and writing logs to local storage. This mismatch is dangerous because users may invoke a seemingly simple reporting skill without realizing it can exfiltrate report contents, persist artifacts, and establish operational behavior beyond passive report generation.

Description-Behavior Mismatch

Medium

• Confidence: 96% confidence
• Finding: The script unconditionally sends the generated stock report to a hard-coded Feishu recipient, regardless of who invoked it or whether the user intended that destination. This creates a clear data exfiltration/privacy risk because user-provided watchlists and generated market analysis are transmitted to a preconfigured external identity without per-use consent or recipient validation.

Context-Inappropriate Capability

Medium

• Confidence: 94% confidence
• Finding: The code has built-in capability to deliver generated content to a fixed third-party Feishu account, but this outbound data flow is not reflected in the described skill behavior. Hidden or undocumented external transmission is dangerous because users and operators cannot make informed trust decisions, and sensitive financial interest information may be disclosed unexpectedly.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The instructions tell the operator to edit a local code file and modify cron without clearly warning that these actions change persistent local system state. In an agent environment, hidden state-changing steps can lead to unintended file modifications, durable task scheduling, and harder-to-audit behavior.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The script sends user-selected stock identifiers to a third-party Eastmoney endpoint over plain HTTP, which exposes request contents to network observers and allows tampering with returned market data. In addition, the skill provides no user-facing disclosure that watchlist contents are being transmitted to external providers, creating a privacy and transparency issue even if the identifiers are not highly sensitive on their own.

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The script sends report contents to Feishu without any user-facing warning, approval prompt, or visible indication that data leaves the local workflow. In the context of a stock-reporting skill, this is more dangerous because watchlists and trading interests can reveal sensitive financial preferences or strategies to an unintended third party.

Session Persistence

Medium

• Category: Rogue Agent

Content

```bash
# 查看当前定时任务
crontab -l

# 编辑定时任务（每天08:30发送）
crontab -e

• Confidence: 97% confidence
• Finding: crontab -l

Session Persistence

Medium

• Category: Rogue Agent

Content

crontab -l

# 编辑定时任务（每天08:30发送）
crontab -e
# 添加：30 8 * * * /root/.openclaw/workspace/skills/stock-daily-report/scripts/send_report.sh >> /tmp/stock_report.log 2>&1
```

• Confidence: 99% confidence
• Finding: crontab -e

VirusTotal

66/66 vendors flagged this skill as clean.

Static analysis

Detected: suspicious.insecure_tls_verification

HTTPS certificate verification is disabled.

Warn

• Code: suspicious.insecure_tls_verification
• Location: scripts/daily_report.py:57