A Stock Evening

Security checks across malware telemetry and agentic risk

Overview

This stock-report skill is mostly coherent, but its send mode needs review because it posts to a fixed Feishu user and uses an unsafe shell command to send externally sourced report text.

Review before installing or enabling --send. Generating the report locally is lower risk; do not add the cron schedule unless the Feishu recipient is verified as yours or made configurable, and prefer a version that sends via a non-shell API or argument-array subprocess call.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Low

Confidence: 87% confidence
Finding: The README explicitly documents a mode that sends generated reports to Feishu, but it does not warn users that running the command causes outbound transmission of report contents to an external service. Even if the data appears routine market information, the skill context includes generated analysis and could later include account-specific or operational data, so the missing disclosure can lead to unintended data sharing.

Missing User Warnings

Medium

Confidence: 97% confidence
Finding: The script sends report content to a hardcoded Feishu user ID when run with --send, without prompting for confirmation or requiring the recipient to be supplied explicitly by the operator. In an agent/skill setting, this creates an unintended data exfiltration path because generated content is transmitted to a fixed external recipient outside the user's control.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal