accelerated-mode
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes an accelerated execution mode that processes external and filesystem data through parallelized subagents, creating a surface for indirect prompt injection.
- Ingestion points: The
smoke-deployed.mjsscript (referenced in SKILL.md) performs real HTTP requests against live deployment URLs to verify state; thebrownfield-scan.mjsscript performs multi-lens filesystem scans of project content. - Boundary markers: The skill establishes high-level boundary markers by requiring human-facing approval for all critical gates (PLAN, BUILD, DEPLOY) and stating that workflow output is advisory rather than decisive.
- Capability inventory: Parallel agents are granted network access for HTTP requests and filesystem read access across the project.
- Sanitization: The instructions do not define specific sanitization, filtering, or escaping mechanisms for the data retrieved from external URLs or scanned files.
Audit Metadata