Back to skill

Security audit

hectorlee-daily-precision-picker

Security checks across malware telemetry and agentic risk

Overview

This stock-screening skill is mostly purpose-aligned, but its helper script can run shell commands built from unvalidated stock-code inputs.

Install only if you trust the candidate-code sources and are comfortable with a skill that runs local shell/npx commands for stock data. Avoid using untrusted pool files or upstream signal files with this version; malformed stock codes could cause unintended shell execution. Treat outputs as screening signals, not investment advice.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (7)

subprocess module call

Medium
Category
Dangerous Code Execution
Content
def run_cmd(cmd, cwd=None, timeout=60):
    """执行命令并返回 stdout 和 success 标记"""
    try:
        result = subprocess.run(
            cmd, shell=True, capture_output=True, text=True,
            timeout=timeout, cwd=cwd
        )
Confidence
97% confidence
Finding
result = subprocess.run( cmd, shell=True, capture_output=True, text=True, timeout=timeout, cwd=cwd )

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill instructs the agent to invoke shell commands (`python screener.py`, `westock-data`, and other tooling) and read local project files such as `references/research_findings.md`, yet the metadata declares no permissions. This mismatch is dangerous because the runtime may grant broader capabilities than users expect, enabling command execution or local file access without transparent permission disclosure or review.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger phrases are very broad (`精选`, `每日优选`, `深度筛选`, `资金确认`, `精筛`, `4层漏斗`) and can match ordinary finance-related requests that are not intended to invoke this skill. That increases the chance of unintended activation of a skill that can execute shell commands and access files, causing unexpected external tool use, data access, or operational side effects in response to generic user prompts.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger phrase "精选" is extremely broad and commonly appears in ordinary Chinese user requests, making accidental or unintended invocation likely. In a finance skill that can influence stock selection behavior, overbroad activation increases the chance that the agent routes unrelated conversations into investment-oriented logic without clear user intent.

Vague Triggers

Medium
Confidence
88% confidence
Finding
Triggers like "每日优选", "深度筛选", "资金确认", "精筛", and "4层漏斗" are ambiguous without domain qualifiers and may match requests outside this skill's intended scope. Because the skill operates in a financial decision-support context, ambiguous invocation can misroute user requests into stock-picking workflows, creating trust, compliance, and safety risks.

Unvalidated Output Injection

High
Category
Output Handling
Content
def run_cmd(cmd, cwd=None, timeout=60):
    """执行命令并返回 stdout 和 success 标记"""
    try:
        result = subprocess.run(
            cmd, shell=True, capture_output=True, text=True,
            timeout=timeout, cwd=cwd
        )
Confidence
98% confidence
Finding
subprocess.run( cmd, shell=True, capture_output

Tool Parameter Abuse

High
Category
Tool Misuse
Content
def run_cmd(cmd, cwd=None, timeout=60):
    """执行命令并返回 stdout 和 success 标记"""
    try:
        result = subprocess.run(
            cmd, shell=True, capture_output=True, text=True,
            timeout=timeout, cwd=cwd
        )
Confidence
97% confidence
Finding
subprocess.run( cmd, shell=True

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.