ib-report-delta-adjusted-notional-exposure
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates locally to process financial data from the Interactive Brokers API and generates a report. No network exfiltration, hardcoded credentials, or obfuscated code were found.
- [COMMAND_EXECUTION]: The skill executes a local Python script (scripts/delta_exposure.py) to retrieve data from the brokerage. The command is static and uses uv for execution, which is standard for this skill's environment.
- [PROMPT_INJECTION]: The skill processes instrument symbols and account data from the brokerage API, which constitutes an indirect prompt injection surface. However, the risk is minimal as the data source is the user's own financial account.
- Ingestion points: Position symbols and account IDs are fetched via scripts/delta_exposure.py.
- Boundary markers: The markdown template lacks specific delimiters to isolate external data from instructions.
- Capability inventory: The agent can read the gathered JSON data and save markdown files to the sandbox/ directory.
- Sanitization: No validation is performed on the data strings returned from the API before they are included in the report template.
Audit Metadata