Is tanjinlimkelvin-dot/ai-hedge-fund safe?
https://clawhub.ai/tanjinlimkelvin-dot/ai-hedge-fund
This AI hedge fund skill provides legitimate financial analysis functionality using multiple AI agent personas, but poses security risks through external code execution requirements. The skill downloads and executes code from an external GitHub repository with system package installation overrides, creating potential attack vectors if the external repository is compromised.
Category Scores
Findings (5)
MEDIUM External Repository Download and Execution -40 ▶
The skill instructs the agent to clone an external GitHub repository and execute Python code from it. This creates a significant security risk as the external repository could be compromised or contain malicious code.
MEDIUM Package Installation with System Override -15 ▶
The skill uses the --break-system-packages flag when installing Python packages, which bypasses package management safety mechanisms and could allow installation of conflicting or malicious packages.
LOW External Network Access Request -12 ▶
The skill requires external network access to clone repositories and potentially make API calls, expanding the attack surface.
LOW Complex Setup Instructions -10 ▶
The skill includes multi-step setup instructions that could potentially be used to mask malicious commands among legitimate ones.
INFO Configuration File Access -8 ▶
The skill reads OpenClaw configuration files to detect the current model, which is legitimate functionality but represents data access.