ito-trade-planner
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for reading external data which acts as a potential surface for indirect prompt injection.
- Ingestion points: Reading Itô basket metadata (SKILL.md).
- Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external metadata as untrusted data.
- Capability inventory: The skill is explicitly described as non-executing and contains no tool-calling logic or subprocess operations.
- Sanitization: No specific sanitization or content validation for the fetched metadata is mentioned.
Audit Metadata