ito-trade-planner
Pass
Audited by Gen Agent Trust Hub on May 29, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill contains no instructions designed to bypass safety filters or override agent behavior. Its primary focus is on establishing a structured workflow for research and planning.
- [CREDENTIALS_UNSAFE]: The skill includes an explicit security rule forbidding the agent from requesting private keys, seed phrases, or other wallet credentials. While it mentions the use of an 'ITO_API_KEY' for reading metadata, this is a standard configuration pattern and no secrets are hardcoded.
- [DATA_EXFILTRATION]: There are no commands or network operations that suggest data is being sent to external or unauthorized destinations. The workflow is restricted to generating checklists and tables within the user session.
- [REMOTE_CODE_EXECUTION]: The skill is explicitly described as 'non-executing' and 'non-advisory.' It does not contain any scripts, package installations, or remote download commands.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user trade ideas and external basket metadata. Although this provides an entry point for untrusted data, the skill mitigates risk by enforcing a non-executing workflow that requires human review before any action is taken.
Audit Metadata