flutter-product-brief
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface where instructions provided by the user during the discovery phase (answering the 10 questions) are interpolated into local documentation files (
docs/product/app_brief.md,user_stories.md,mvp_scope.md). - Ingestion points: User responses to discovery questions in
SKILL.md. - Boundary markers: The generated Markdown templates lack explicit delimiters or instructions to ignore embedded commands within the user-provided data.
- Capability inventory: The skill possesses file-write capabilities to the
docs/product/directory. - Sanitization: No explicit sanitization or validation of the user-provided content is defined before it is written to the artifacts.
Audit Metadata