create-app
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements a session-resume mechanism by reading existing project documentation.
- Ingestion points: Artifacts in the
docs/folder, specificallydocs/CREATE-APP-PLAN.md, are read during the 'Resume first' operating rule inSKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the documentation templates.
- Capability inventory: The skill can read/write files in the
docs/directory and invoke other agent skills via their slugs. - Sanitization: Content read from the
docs/folder is processed without explicit sanitization or verification against a schema. - [EXTERNAL_DOWNLOADS]: The skill suggests the use of
npx skills add wondelai/skills/<slug> --globalif a specific phase-related skill is missing. This command targets the vendor's own repository and is a standard procedure for expanding the agent's capabilities.
Audit Metadata