ito-basket-compare

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied research theses, portfolio notes, and CRM context. These external data sources can contain hidden instructions that might influence the agent's logic or output format.
  • Ingestion points: The skill is designed to ingest and compare content from the user's knowledge base, portfolio notes, research memos, and CRM context as specified in the comparison modes.
  • Boundary markers: The instructions do not define specific delimiters (like XML tags or triple quotes) or explicit instructions for the agent to ignore commands embedded within the ingested data.
  • Capability inventory: The skill is restricted to read-only data access and specific market data retrieval via the Itô API; it lacks capabilities for local file writing, shell command execution, or arbitrary network exfiltration.
  • Sanitization: No explicit sanitization, validation, or filtering logic is defined for the text ingested from external notes or documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 03:40 PM
Security Audit — agent-trust-hub — ito-basket-compare