stock-tech-analysis
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes user-provided data from CSV files which is a potential surface for indirect prompt injection. However, the implementation in
scripts/compute_indicators.pyincludes robust sanitization by explicitly coercing input columns to numeric types (pd.to_numeric) and dropping rows with invalid data, which effectively neutralizes attempts to inject malicious text instructions via data columns. - [COMMAND_EXECUTION]: The skill defines a local Python script for data processing. This is the primary intended functionality, and the script uses standard argument parsing to handle file paths without risks of shell injection or unsanitized input execution.
- [EXTERNAL_DOWNLOADS]: The documentation suggests installing well-known, official packages (
pandas,numpy) from standard registries. No remote scripts are downloaded or executed at runtime.
Audit Metadata