build-scaffold
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted input from the project startup context to generate file structures and install dependencies without using boundary markers or sanitization to prevent malicious instructions in the input from influencing the AI's file-writing behavior.
- Ingestion points: Project startup event (
ON:project_start) and implicit user project requirements. - Boundary markers: None detected in the skill instructions.
- Capability inventory: File system writing (
create_all_files_at_once) and command execution for dependency installation. - Sanitization: No validation or sanitization of project requirements is specified.
Audit Metadata