Wallets
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The catalog.json file defines an installation command using curl to fetch remote content from https://ethskills.com/wallets/SKILL.md. It also references a plugin installation from a GitHub repository (https://github.com/austintgriffith/ethskills).\n- [PROMPT_INJECTION]: The setup instructions direct the AI agent to ingest data from an external URL, creating a surface for indirect prompt injection.\n
- Ingestion points: Content is retrieved from ethskills.com via curl and direct agent reading.\n
- Boundary markers: No delimiters are present to identify external content boundaries.\n
- Capability inventory: No dangerous system or network capabilities are defined in the skill files.\n
- Sanitization: No content validation or escaping is applied to the remote data.
Audit Metadata