monorepo-architect

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill contains an instruction to open resources/implementation-playbook.md for detailed examples. This represents a potential indirect prompt injection vector as the agent processes content from an external source without explicit boundary markers or sanitization. * Ingestion point: resources/implementation-playbook.md. * Boundary markers: Absent. * Capability inventory: Workspace configuration, task orchestration, and build caching suggestions. * Sanitization: Absent.
  • [NO_CODE]: The provided skill file contains no executable scripts, shell commands, or binary files. It consists entirely of markdown metadata and instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 01:42 AM