arize-link
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the ax CLI tool to discover organization and project information by executing commands such as ax organizations list and ax projects list.
- [INDIRECT_PROMPT_INJECTION]: The skill presents a command injection surface by interpolating potentially untrusted identifiers directly into shell commands, specifically when listing projects via ax projects list --space "{space_name_or_id}". If the input contains shell metacharacters, it could lead to unauthorized command execution. * Ingestion points: User-provided identifiers or identifiers extracted from external data sources. * Boundary markers: None provided to separate untrusted input from the shell command structure. * Capability inventory: Access to the ax CLI tool for platform resource discovery. * Sanitization: The instructions specify base64-encoding for URL components but do not provide sanitization or validation requirements for the variables passed as CLI arguments.
Audit Metadata