exotic-derivatives
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external market data from CSV files and interpolates the results into the agent's context through a JSON diagnostic report.
- Ingestion points: The
scripts/exotic_derivatives_diagnostics.pyscript reads user-provided CSV files (e.g.,input.csv) viapd.read_csv. - Boundary markers: None. The skill does not provide instructions to the agent to ignore or delimit potentially malicious content within the processed data.
- Capability inventory: The skill includes
scripts/exotic_derivatives_diagnostics.pywhich has file-read (CSV) and file-write (JSON output) capabilities via standard Python libraries. - Sanitization: The script performs basic type conversion (to numeric/datetime) and drops invalid rows, but it does not sanitize string-based content (like the
instrumentcolumn) which is then reflected back in the output JSON.
Audit Metadata