The Agent Skills Directory

[COMMAND_EXECUTION]: The script constructs file paths for chart generation using the user-supplied stock symbol without sanitization, which can lead to path traversal vulnerabilities.
Evidence: In scripts/yf.py, the functions save_pro_chart and main (for simple charts) use the symbol variable to build output paths: path = f"/tmp/{symbol}_pro.png" and path = f"/tmp/{symbol}_simple.png". An adversarial input such as ../etc/cron.d/task could potentially be used to write files to unauthorized locations on the file system.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from an external API, creating a surface for indirect prompt injection attacks.
Ingestion points: The skill fetches real-time market quotes, fundamental metrics, and historical price data from the Yahoo Finance API via the yfinance library in scripts/yf.py.
Boundary markers: The instructions do not define clear delimiters or include warnings to the agent to ignore instructions that might be embedded in company names, descriptions, or other metadata fields returned by the API.
Capability inventory: The skill has the capability to perform network requests and write files to the local system (/tmp/ directory).
Sanitization: The script processes financial data using standard libraries (pandas, rich) but does not perform specific sanitization or escaping of string-based fields (like company names) before they are rendered into the agent's context.

stock-info-explorer