review-fi-portfolio-workflow

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were detected in the skill instructions. No unauthorized network requests, credential access, or persistence mechanisms are present.
  • [PROMPT_INJECTION]: The skill was evaluated for indirect prompt injection risks associated with processing user-provided data.
  • Ingestion points: User-supplied bond identifiers (ISIN, CUSIP, RIC), position sizes, and scenario parameters defined in the 'Gather Portfolio Holdings' section.
  • Boundary markers: No explicit delimiters or instructions to ignore potential embedded commands within the bond identifier data are present in the workflow.
  • Capability inventory: The skill utilizes specialized financial tools including bond_price, yieldbook_bond_reference, yieldbook_cashflow, yieldbook_scenario, and interest_rate_curve for data retrieval and calculation.
  • Sanitization: No explicit input validation or escaping logic is defined for the identifiers before they are passed to the analytical tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 03:07 AM
Security Audit — agent-trust-hub — review-fi-portfolio-workflow