ib-report-delta-adjusted-notional-exposure
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes financial data retrieved from the Interactive Brokers API to generate user-facing markdown reports, which creates a surface for indirect prompt injection if external data (such as account names or symbol strings) contains malicious instructions.
- Ingestion points: Data enters the agent context through the JSON output of
scripts/delta_exposure.py(which fetches data via thetrading_skillslibrary). - Boundary markers: The instructions do not define clear boundaries or delimiters to prevent the agent from interpreting content within the portfolio data as new instructions.
- Capability inventory: The skill possesses the capability to execute Python scripts, read template files, and write reports to the
sandbox/directory. - Sanitization: There is no evidence of data validation, escaping, or sanitization of the values retrieved from the API before they are rendered into markdown format.
Audit Metadata