ito-basket-compare
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill is designed to handle sensitive user data, including portfolio notes, financial context, holdings summaries, and research memos. It includes instructions to preserve privacy by summarizing only necessary fields and specifies using
ITO_API_KEYexclusively for read-only data retrieval from Itô market sources. No automated network exfiltration of this data is programmed. - [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests and processes potentially untrusted content from user-provided notes and documents.
- Ingestion points: User knowledge base, portfolio notes, research memos, CRM context, and financial context mentioned in SKILL.md.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' warnings for the external user data being processed.
- Capability inventory: The skill is restricted to read-only comparison and analysis; it does not request file-writing, subprocess execution, or arbitrary network access tools.
- Sanitization: There are no explicit instructions for sanitizing, escaping, or validating the content retrieved from external documents before it is processed by the agent.
Audit Metadata