T08 · Insecure Dependencies
- Location
SKILL.md:117- Finding
Unpinned Third-Party Dependencies Permit Mutable Supply-Chain Code
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
The skill presents itself as live financial monitoring, but its reports are mostly hard-coded current-dated market claims, so users could mistake sample data for real investment signals.
Review this carefully before installing. It does not appear to steal data or install a backdoor, but it should not be treated as a reliable market-monitoring tool until live data parsing, source timestamps, failure handling, and dependency pinning are added. Avoid using its output for investment decisions in its current form.
SKILL.md:117Unpinned Third-Party Dependencies Permit Mutable Supply-Chain Code
scout.py:21Current-Dated Financial Report Contains Hard-Coded and Unvalidated Market Claims
The skill defines a generic helper that can execute arbitrary shell commands despite its advertised purpose being market monitoring and report generation. This capability is over-privileged for the task and creates a dangerous primitive that could be repurposed for command execution if the code is modified, extended, or integrated with external inputs.
This finding is valid because the skill exposes a tool-like primitive that executes shell commands with shell=True, a classic avenue for tool-parameter abuse and command injection. Even though current calls are hardcoded curl commands, the existence of this primitive in a market-reporting skill is unjustified and becomes more dangerous if any argument source becomes user- or data-controlled.
def run_command(cmd):
"""执行 shell 命令并返回结果"""
try:
result = subprocess.run(cmd, shell=True, capture_output=True, text=True, timeout=30)
return result.stdout.strip()
except Exception as e:
return f"Error: {e}"
The skill advertises shell-based installation and runtime commands, plus cron execution and pip dependency installation, but does not declare any explicit tool scope such as permissions or allowed-tools. This creates an ambiguity gap where an agent or platform may permit shell execution more broadly than users expect, increasing the risk of unintended command execution or unsafe automation.
This code file contains natural-language descriptions and CLI help that force a specific language/locale for all users. Under the policy, a skill should not mandate a language without user opt-in unless the locale constraint is clearly documented and justified.
The code invokes subprocess.run with shell=True, which is inherently risky because any future or indirect use of untrusted input in cmd can lead to shell injection and arbitrary command execution. In this skill’s context, shell execution is unnecessary for ordinary market-data retrieval and expands the attack surface beyond the stated functionality.
def run_command(cmd):
"""执行 shell 命令并返回结果"""
try:
result = subprocess.run(cmd, shell=True, capture_output=True, text=True, timeout=30)
return result.stdout.strip()
except Exception as e:
return f"Error: {e}"
The manifest says the skill automatically monitors A/H-share anomalies, financial news, and hot sectors to generate investment opportunity briefs. Aside from two curl calls whose results are not parsed or used, the report is built from fixed hard-coded sectors, stocks, news, and hints, so the actual behavior does not match the claimed monitoring capability.
Several docstrings say the code 'gets' hot sectors, unusual stocks, finance news, and opportunity hints, and the module docstring says it 'automatically monitors' market movements. In reality, these functions print static, hard-coded lists rather than retrieving or monitoring real-time data, which contradicts the documented intent rather than merely omitting implementation detail.
The manifest description and the user-facing README content consistently force Chinese-language interaction and documentation. Under the policy, language constraints should either be optional for the user or clearly justified as region-specific; this file does neither explicitly.