skills/affaan-m/ecc/ito-baskets/Gen Agent Trust Hub

ito-baskets

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is strictly limited to indexing, comparing, and briefing market data. It contains explicit non-negotiable boundaries that prohibit order execution, investment advice, or any state-changing operations.
  • [COMMAND_EXECUTION]: Data retrieval is handled via a local script scripts/ito-baskets.js. The script is dependency-free, uses only Node.js built-ins, and is restricted to making GET requests. It includes validation logic to ensure API base URLs use HTTPS and targets only the official vendor domain.
  • [PROMPT_INJECTION]: The skill handles an indirect prompt injection surface by ingesting untrusted data from the Itô Markets API and user-supplied research notes. However, it mitigates this risk by instructing the agent to treat fetched content as untrusted, ignore embedded instructions, and perform Unicode NFKC normalization on inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 08:45 PM
Security Audit — agent-trust-hub — ito-baskets