tauri-app-planning
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's workflow involves analyzing user-supplied requirements and mapping them to a technical design document and a todo list. This process creates a surface for indirect prompt injection where malicious instructions embedded in the user requirements could influence the agent's output or be persisted in the generated tasks.
- Ingestion points: User-provided application requirements, platform choices, and core feature descriptions analyzed during the 'Requirement Analysis' phase in
SKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or specific system prompts to ignore potential instructions embedded within the user data during processing.
- Capability inventory: The skill explicitly instructs the agent to use the
TodoWritetool to generate a persistent 'Execution Plan' based on the analyzed requirements. - Sanitization: There are no instructions for the agent to sanitize, escape, or validate the user-provided input before interpolating it into the final design document or task list.
Audit Metadata