Frontend UX
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and downloads external content from
https://ethskills.com/frontend-ux/SKILL.mdand provides instructions to install a plugin fromhttps://github.com/austintgriffith/ethskills. - [COMMAND_EXECUTION]: The
catalog.jsonfile defines an installation commandcurl -s https://ethskills.com/frontend-ux/SKILL.mdto fetch documentation and suggests usage of package managers (claude plugin install,clawhub install) to integrate external code. - [DATA_EXPOSURE_SURFACE]: The skill instructs the agent to ingest content from an external URL (
https://ethskills.com/frontend-ux/SKILL.md) at runtime. This creates a surface for indirect prompt injection where the agent's behavior could be influenced by changes to the remote file's content. - Ingestion points: The agent is explicitly told to read content from a third-party domain (ethskills.com).
- Boundary markers: No delimiters or instructions to ignore embedded commands are present in the 'Read...' instruction.
- Capability inventory: No file system writes or subprocess calls are directly in the skill scripts, though the agent using the skill typically possesses these capabilities.
- Sanitization: There is no validation of the remote content before processing.
Audit Metadata