Why Ethereum
Warn
Audited by Gen Agent Trust Hub on Jul 5, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
curlto fetch content fromhttps://ethskills.com/why/SKILL.mdduring the installation process defined incatalog.json. - [REMOTE_CODE_EXECUTION]: The
setupfield incatalog.jsonprovides commands to install a plugin directly from an external GitHub repository (github.com/austintgriffith/ethskills), which executes code from a third-party source. - [PROMPT_INJECTION]: The skill instructs the agent to ingest content from an external URL (
https://ethskills.com/why/SKILL.md), creating a surface for indirect prompt injection. - Ingestion points: Remote URL processing requested in the
setupinstructions ofcatalog.json. - Boundary markers: Absent; instructions do not include delimiters or warnings to ignore embedded commands in the fetched content.
- Capability inventory: The skill facilitates external tool installation and network fetching via
curland platform-specific plugin managers. - Sanitization: Absent; fetched content is intended to be processed directly by the agent without filtering or validation.
Audit Metadata