finhay-portfolio

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a local script ./finhay.sh to execute API requests, perform system health checks (doctor), and resolve user identifiers (infer).
  • [EXTERNAL_DOWNLOADS]: The CLI includes a sync command intended to update local skill definitions from an external source, functioning as a remote update mechanism.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by processing external data from API responses, such as order feedback messages (feedbackmsg) and stock names, without utilizing boundary markers or sanitization logic. Mandatory Evidence Chain:
  • Ingestion points: references/endpoints/order-book.md (feedbackmsg field), references/endpoints/orders.md (symbol and market_price fields).
  • Boundary markers: Not present in SKILL.md or endpoint references.
  • Capability inventory: Subprocess execution via ./finhay.sh in SKILL.md.
  • Sanitization: Not specified in the instructions for handling API responses.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 02:58 AM
Security Audit — agent-trust-hub — finhay-portfolio