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 --yesto 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 prepareor the/harness-preparecommand 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/, anddocs/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