webcraft-wireframe
Warn
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill is configured to dynamically fetch and apply guidance from external SKILL.md files hosted on a third-party GitHub repository (github.com/jakubkrehel/skills). This mechanism allows external instructions to influence the agent's behavior at runtime, effectively acting as a remote prompt loader from an untrusted source.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from the local project environment, which could contain malicious instructions designed to manipulate the agent's output or actions.\n
- Ingestion points: The skill reads files including 00-project.md, project briefs, plans, and draft copy to inform its wireframing process (as specified in SKILL.md).\n
- Boundary markers: Absent. There are no specific delimiters or instructions defined to prevent the agent from obeying embedded commands within the ingested content.\n
- Capability inventory: The skill has the capability to write and modify files in the project directory, use package managers (npm, yarn, pnpm), scaffold frameworks (Vite, Tailwind), and inspect running terminals and environment files.\n
- Sanitization: No validation or sanitization of the content from ingested files is performed before it is used to generate code or structure pages.
Audit Metadata