nextstage-spec-driven

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends the execution of npx @nextstage-brasil/harness --preset complements --yes to install additional complement skills. This command fetches and executes packages from the NPM registry.
  • [COMMAND_EXECUTION]: Instructions are provided to guide the user to manually run npx @nextstage-brasil/harness prepare or the /harness-prepare command for project initialization and brownfield onboarding.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing external project data.
  • Ingestion points: Files read from docs/versions/{version_san}/, docs/context/, and docs/specs/ (e.g., requirements.md, task-NNN-*.md, design-brief.md, architecture-rules.md).
  • Boundary markers: None identified. The skill reads the files directly into the context as authority for the current version's state.
  • Capability inventory: Subprocess execution via delegated workers (code-coder, code-autonomous, execution-orchestrator), file system writes for artifact generation, and recommendation of shell commands (npx).
  • Sanitization: No evidence of content sanitization or validation before interpolation into the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 08:25 PM
Security Audit — agent-trust-hub — nextstage-spec-driven