mirofish-prediction
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for running local scripts and services, including a Python backend and an NPM-managed frontend (e.g.,
python backend/app/main.pyandnpm start). These are standard development operations for local project setup. - [SAFE]: Instructions regarding API key management involve storing secrets in a local
.envfile (~/Projects/MiroFish/.env). This aligns with security best practices for local development and does not involve hardcoding or exfiltrating credentials. - [SAFE]: The skill identifies a potential attack surface for indirect prompt injection as it processes untrusted external data (news, market signals, policy changes). This is a known risk factor for simulation and research tools rather than an active malicious exploit in the skill code.
- Ingestion points: External seed data (news, market signals) described in
SKILL.md. - Boundary markers: None specified in the provided instructions.
- Capability inventory: The skill instructions do not invoke agent tools directly but describe execution of a local software package.
- Sanitization: Not explicitly mentioned in the setup instructions.
Audit Metadata