skills/afonsoft/skills/scaffold-mvp/Gen Agent Trust Hub

scaffold-mvp

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill performs standard project scaffolding tasks using official ecosystem tools including dotnet CLI, npm, and Angular CLI.
  • [SAFE]: The instructions mandate the use of mature, established UI libraries such as MudBlazor, Radzen, Angular Material, and PrimeNG, reducing the risk associated with custom or obscure implementations.
  • [SAFE]: Security best practices are enforced, such as pinning exact dependency versions and using .env.example templates for secret management.
  • [SAFE]: The skill references the author's official repository at github.com/afonsoft/skills for its skill collection context.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local documentation and specification files to drive the scaffolding logic.
  • Ingestion points: Phase 1 reads external content from .claude/CONTEXT.md and .specs/SPEC-*.md.
  • Boundary markers: No specific delimiters or "ignore instructions" markers are defined for the ingested files.
  • Capability inventory: The skill has capabilities for file system writes, project solution generation, and package installation.
  • Sanitization: The risk is mitigated by a mandatory Phase 2 validation step where the agent must obtain explicit user approval in Portuguese before executing any scaffolding commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 01:05 AM
Security Audit — agent-trust-hub — scaffold-mvp