depositary-receipts-adr-gdr
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The primary functional component,
scripts/depositary_receipts_adr_gdr_diagnostics.py, is a standard Python script for data analysis. It uses thepandaslibrary to perform statistical calculations (means, standard deviations, correlations, and drawdowns) on local CSV data. The script does not initiate network requests, access sensitive system directories, or execute arbitrary shell commands. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data via a CSV ingestion point, which presents a surface for indirect prompt injection if the resulting JSON output is later interpreted as instructions by the agent.
- Ingestion points:
scripts/depositary_receipts_adr_gdr_diagnostics.pyreads the file specified in theinput_csvargument. - Boundary markers: Absent; the skill instructions do not specify delimiters to separate tool output from agent instructions.
- Capability inventory: The skill has the ability to write JSON artifacts to the local file system.
- Sanitization: Absent; while the script attempts to convert columns to numeric types, it does not sanitize or validate string content within the input file before processing.
Audit Metadata