Testing
Pass
Audited by Gen Agent Trust Hub on Jul 5, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's installation and setup process fetches documentation from
https://ethskills.com/testing/SKILL.mdusingcurl. - [REMOTE_CODE_EXECUTION]: The
catalog.jsonfile includes setup instructions for installing a plugin from a third-party GitHub repository (https://github.com/austintgriffith/ethskills), which involves executing externally hosted code. - [PROMPT_INJECTION]: The skill creates an indirect prompt injection surface by instructing the agent to read external instructions from
https://ethskills.com/testing/SKILL.md. This allows remote content to potentially influence the agent's behavior at runtime. - Ingestion points: Remote markdown file at
https://ethskills.com/testing/SKILL.md. - Boundary markers: None specified.
- Capability inventory: Not applicable (documentation focused).
- Sanitization: None.
Audit Metadata