empjs-skill
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates the download and installation of external packages via the
eskill installcommand. It supports fetching content from Git URLs, NPM packages, and local directories. - [COMMAND_EXECUTION]: The skill converts user natural language into shell commands (e.g.,
eskill install,eskill list,eskill remove) for execution. It provides specific syntax guidance for different environments like PowerShell and Bash. - [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection by interpolating untrusted user input directly into shell commands.
- Ingestion points: User natural language requests and intent extraction for parameters like skill names or URLs.
- Boundary markers: None identified; the skill instructions do not specify delimiters to separate user data from command templates.
- Capability inventory: Execution of the
eskillCLI, which has the capability to modify the filesystem, install software, and perform network operations. - Sanitization: No explicit sanitization or validation of URLs or package names is described in the workflow.
Audit Metadata