taubyte-project-and-application
Pass
Audited by Gen Agent Trust Hub on Apr 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
tauCLI tool to create and manage projects and applications. It passes user-provided strings for project names and descriptions directly as shell command arguments. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted user data (names and descriptions) and uses them to drive shell commands without defined sanitization or boundary markers.
- Ingestion points: User-provided project names, application names, and descriptions in
SKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used when interpolating user variables into CLI commands.
- Capability inventory: Shell command execution via the
tauCLI across multiple steps inSKILL.md. - Sanitization: No input validation or escaping logic is specified for the user-supplied variables.
Audit Metadata