fsi-command-review-fi-portfolio

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The instruction set describes a legitimate business process for financial analysis. No malicious behaviors such as credential theft, remote code execution, or persistence mechanisms were found.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing user-provided bond identifiers. This is documented as a common attack surface for data-processing skills.
  • Ingestion points: User-supplied bond identifiers (ISINs, CUSIPs, RICs) are collected in the initial workflow step (SKILL.md).
  • Boundary markers: None are defined to separate user input from the system's execution logic.
  • Capability inventory: The workflow is limited to financial data retrieval and analysis tools (bond_price, yieldbook_bond_reference, yieldbook_cashflow, yieldbook_scenario, interest_rate_curve). No high-risk actions like file modification or subprocess execution are present.
  • Sanitization: Input validation or escaping of the user-provided identifiers is not specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 03:45 PM
Security Audit — agent-trust-hub — fsi-command-review-fi-portfolio