base44-cli
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill operates by executing the base44 CLI tool through package managers. It includes a specific functionality to execute scripts via the base44 exec command which reads from standard input.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. Ingestion points: The agent reads configuration from base44/config.jsonc and entity schemas in base44/entities/ as defined in SKILL.md. Boundary markers: None identified. Capability inventory: The agent can execute shell commands via npx and run scripts via base44 exec. Sanitization: No sanitization or validation of input files is described in the instructions.
- [SAFE]: The skill implements a security-first approach by requiring an identity check via base44 whoami before any operations are performed.
- [SAFE]: All external dependencies and network endpoints are associated with the official vendor infrastructure.
Audit Metadata