ClawHub
Back to skill

Security audit

Stock Planner

Security checks across malware telemetry and agentic risk

Overview

This skill is a local stock-position analysis tool that reads user-supplied files and optionally writes a requested JSON plan, with no evidence of network access, credential use, persistence, or account-changing actions.

Install only if you are comfortable giving the agent local access to the specific holdings, price, or plan files you ask it to analyze. Treat its output as informational trading-risk guidance, not automated financial advice, and use explicit file paths and output locations.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding
The skill advertises local CSV-based analysis but does not declare permissions even though its documented usage includes reading input files and writing JSON output. Undeclared file capabilities reduce transparency and can cause the agent platform or user to authorize behavior they did not explicitly review, which is a security and trust boundary issue.

Tp4

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding
A description-behavior mismatch is a real security concern because users may invoke a seemingly simple trade-planning skill while hidden or undocumented capabilities perform materially broader analysis or create artifacts on disk. In a finance context, features like leverage stress testing, history analysis, correlation analysis, rebalance logic, and file export expand the data processed and actions taken, increasing the chance of unexpected access, unsafe recommendations, or misuse beyond the user's informed consent.

Vague Triggers

Medium
Confidence
80% confidence
Finding
Broad trigger keywords can cause accidental invocation for generic finance conversations, pulling user portfolio files or generating trading guidance when the user did not intend to use this skill. Because the skill operates on sensitive financial holdings and may read local files, ambiguous activation increases the risk of unnecessary data exposure and inappropriate automation.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.