tauri-app-frontend-selection
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The template file
templates/basic.mdcontains several interpolation placeholders such as{dev_url},{dist},{build_cmd}, and{preview_cmd}. These represent an indirect prompt injection surface where untrusted data (e.g., a URL or build command provided by a user) is inserted into a prompt context without explicit boundary markers or sanitization, potentially allowing an attacker to influence the agent's behavior through the processed output. - Ingestion points: Placeholders in
templates/basic.mdused for rendering final output. - Boundary markers: None detected surrounding the interpolated variables.
- Capability inventory: The skill is designed to provide shell commands and configuration rationale, which are often executed or adopted by the agent.
- Sanitization: No explicit sanitization or validation logic is defined for the placeholder values.
- [SAFE]: All external references in
SKILL.mdpoint to the official Tauri documentation domain (v2.tauri.app), which is a well-known and trusted service. These links are documented neutrally and do not contribute to risk escalation.
Audit Metadata